Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate mutability (readOnlyHint=false, destructiveHint=false). The description adds critical behavioral context: notes are add-only, no edit or delete support, and provides a detailed return JSON structure. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with sections, front-loaded with purpose and important constraints, and uses examples. Slightly verbose with 'This is a V1 API endpoint' but overall efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 6 parameters, no output schema, and moderate complexity, the description covers all aspects: required/optional parameters, return format, examples, use cases, and cross-references to sibling tools for ID lookups. Very complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and descriptions are present, but the description adds significant value: clarifies required combination of parameters, provides HTML examples, a full example with companyIds, and cross-references sibling tools for ID retrieval.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a new note attached to companies, persons, or opportunities, and specifies it's a V1 API endpoint. It distinguishes from sibling tools like affinity_list_company_notes which are read-only listing operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly warns that notes are add-only (no edit/delete), lists required and optional parameters, and provides use cases. It does not explicitly mention alternatives for editing/deleting but implies through context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate a write operation (readOnlyHint=false), and the description adds that created companies are always custom (global=false), explains the return format, and mentions the V1/V2 API difference. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with clear sections (Required, Optional, Important, Returns, Example Workflow). Every sentence provides value; no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers prerequisites, behavioral traits, return format, and post-creation usage. With no output schema, it fully documents the return object and example workflow, making it complete for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description adds value by clarifying domain as 'Primary domain' with an example, and notes the purpose of responseFormat. Slightly above baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Create a new company (organization) in Affinity,' with a specific verb and resource. It distinguishes from sibling tools like affinity_create_person and affinity_search_companies by mentioning API version differences and suggesting a workflow.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises to use affinity_search_companies first to check existence, notes that global companies cannot be created, and provides an example workflow. Names alternatives and gives clear when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate write operation (readOnlyHint=false) and not idempotent. Description adds context: V1 only, duplicate email handling, return structure, and example workflow. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with sections: purpose, API version, required/optional fields, important notes, return example, workflow. Some redundancy but every section adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Comprehensive for a creation tool without output schema. Covers all parameters, error conditions, return format, and integration with other tools (search, get, add note).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds meaning: first email becomes primary, duplicate emails cause 422, organizationIds associate person. Clarifies responseFormat optional.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Create a new person (contact) in Affinity' with specific verb and resource. It distinguishes from siblings like affinity_search_persons and affinity_create_company.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use: creating a person. Includes workflow: search first, then create if not found. Warns about duplicate emails and suggests using affinity_search_persons before creation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, non-destructive, idempotent. Description adds transparency about client-side filtering and API limitations, which is valuable beyond annotations. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with headers, bullet points, code block, and use cases. Length is justified by the amount of useful information. Could be slightly shorter but every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (client-side filtering, pagination, workflow), the description is quite complete. Provides sample return JSON, workflow steps, and behavioral notes. No output schema but compensates with detailed return description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions. Description enhances parameters by explaining how to obtain listId and swimlaneId, default/max for limit, and the role of cursor. Adds context beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get all companies at a specific pipeline stage (swimlane)' with a specific verb and resource. It distinguishes from siblings like affinity_list_companies by focusing on stage filtering, and the workflow helps differentiate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides a clear workflow (list lists, get swimlanes, then this tool) and use cases. Mentions client-side filtering and pagination for large lists. Lacks explicit when-not-to-use instructions but context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true, destructiveHint=false. The description adds rich behavioral details: return structure, field categories (enriched vs global), and example field IDs. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with headings and bullet points. It is slightly lengthy due to the full return schema example, but every part is informative and earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite lacking an output schema, the description provides a complete return JSON schema, covers optional parameters, and explains field types. It fully equips the agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, yet the description adds significant value: explains the interaction between fieldTypes and fieldIds, provides example field IDs, and clarifies the default behavior without these parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get a single company by ID from Affinity CRM.' The verb 'get' and resource 'company' are specific. It distinguishes from sibling tools like affinity_list_companies (which lists all companies) and affinity_get_company_list_entries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the effect of optional parameters (fieldTypes/fieldIds) on the response, guiding when to use them. It implies usage for fetching a single company by ID but lacks explicit when-not or alternative comparisons.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds value beyond annotations by detailing the return type, empty array behavior for companies not on lists, and the categories of fields included, which are not covered by readOnlyHint, destructiveHint, etc.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with purpose upfront, followed by return format, parameters, use cases, and field types. It is somewhat lengthy but each section adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is very complete, providing a full JSON response example, covering edge cases (empty array), and detailing all field categories, compensating for the lack of an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description enhances parameter understanding with context like where to obtain companyId, default/limits for limit, and pagination guidance, though responseFormat is only in schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves all list entries for a company across all lists with full field data, distinguishing it from sibling tools like affinity_get_list_entries which are for single lists.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

While the description lists use cases and implies scope, it does not explicitly state when to use this tool versus alternatives or when not to use it, leaving the agent to infer from context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description explains the return format with a JSON example, pagination parameters, and the common scenario of an empty array. Annotations already provide readOnlyHint, idempotentHint, etc., so the description adds context without contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with sections for parameters, return format, notes, use cases, and next steps. It is concise without unnecessary information, and each part serves a purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite the absence of an output schema, the description includes a detailed JSON return example, covering all fields. It also provides use cases and next steps, making it complete for a read-only list retrieval tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds value by explaining the source of companyId (get from affinity_search_companies or affinity_get_company) and default/max for limit. However, the description omits the responseFormat parameter, which is only in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get all lists where a specific company appears.' It uses a specific verb and resource, and distinguishes itself from sibling tools like affinity_get_company_list_entries or affinity_get_list by focusing on lists containing a specific company.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context for usage, such as 'Useful for discovering which deal pipelines track a specific company.' It also includes a note about empty returns and suggests next steps like using affinity_get_company_list_entries, but it does not explicitly state when to avoid using this tool or list alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (readOnly, idempotent), description reveals that API may return all results regardless of page_size, details error cases, and notes field-specific limitations. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with headers, bullet points, and examples. Front-loaded core purpose. Slightly verbose but every section adds value; could trim redundant examples.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Thorough coverage of return format, use cases, error handling, and edge cases. No output schema, but description compensates fully. Comprehensive for a tool with 7 parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds meaning: explains action_type enum values, warns about API ignoring page_size, clarifies required vs optional, and provides context for each parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves change history for a specific field, detailing who changed what and when. It distinguishes itself from siblings like affinity_get_field_values by focusing on audit trail.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance on when to use (tracking changes, specific use cases), when not (fields without support), and alternatives (use affinity_get_list_fields to find field IDs). Includes error handling and suggestions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds significant behavioral context beyond annotations: V1-only endpoint, field name resolution requirement, global vs list-specific fields, field type enum, full return structure with JSON example, and error handling. Annotations declare readOnlyHint=true, which is consistent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with sections, front-loaded with purpose. Some redundancy (e.g., parameter list repeated), but each section adds value. Could be slightly more concise but informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all essential aspects: API version, constraints, data types, return structure (with JSON example), field resolution, error handling. No output schema provided but the JSON example serves as a surrogate. Complete for a complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with parameter descriptions. The description adds details: exactly one required, consequences of violation, entity-specific examples, and responseFormat enum values. Provides practical guidance beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Retrieve' and the resource 'field values for a specific entity', distinguishing it from sibling tools like `affinity_get_company` or `affinity_get_list_fields`. It lists the four entity types and uses cases.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit constraints ('exactly one entity parameter required'), error conditions (422), and use cases (get company fields, inspect pipeline). Lacks explicit comparison to alternatives but context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint. Description adds return structure (JSON with fields) and explains list types, which provides behavioral context beyond annotations. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with main sentence, returns, list types, and next steps. Some redundancy with schema parameter descriptions, but overall efficient and front-loaded with purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description provides sample JSON output and list types. Includes next steps for further actions. Complete for a simple read tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 2 parameters with 100% description coverage. The description adds extra context that listId 'get from affinity_list_lists', which is helpful. Baseline 3, but the additional guidance justifies a 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Get metadata for a single Affinity list (deal pipeline).' Specifies the resource (list) and verb (get), and distinguishes from siblings like affinity_list_lists and affinity_get_list_entries by focusing on a single list's metadata. Includes return fields and list types for clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context: listId comes from affinity_list_lists. Includes 'Next Steps' with suggested tools based on returned data. Does not explicitly state when not to use, but the function is specific enough that it's clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes beyond annotations by detailing pagination (hasMore, nextCursor), nesting of fields, and that fieldTypes parameter controls whether data is returned. All behavioral disclosures are consistent with readOnly and idempotent annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with a clear front-loaded purpose and organized output schema. The extensive JSON example is informative but slightly verbose; however, every element serves a purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Provides a comprehensive view: output format, pagination, field types, and constraints (e.g., default limit, max). No output schema exists, so the description compensates fully. All necessary context for a 6-parameter read tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description adds value by explaining the effect of fieldTypes (enriched, global, list) and the nesting of fields, which helps clarify parameter usage beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it retrieves entries from an Affinity list, specifying that entries represent companies, people, or opportunities. Distinguishes from siblings like affinity_get_list (list metadata) and affinity_get_company_list_entries (specific to a company).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage by describing the tool's action and including field type explanations, but lacks explicit guidance on when to use this tool versus alternatives like affinity_get_company_list_entries or when to avoid using it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true and idempotentHint=true, which the description supports by describing a read-only operation. The description adds value beyond annotations by detailing the return structure, field classification, value types, and pagination behavior (cursor, limit). However, it omits the responseFormat parameter, which is a minor gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured: a concise first-line summary, bullet points for parameters, a clear JSON example for the return value, and separate sections for field and value types. Every sentence adds value without redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema, the description provides a complete output example with all relevant fields and types. Combined with thorough annotations (readOnly, idempotent) and full parameter coverage, it leaves no major gaps for a standard read-only list fields retrieval tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, baseline is 3. The description adds context for listId (source from affinity_list_lists) and explains pagination parameters (cursor, limit). This extra clarification improves the agent's understanding beyond the schema alone. The responseFormat parameter is not described, but its presence in the schema is sufficient given high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get field definitions for an Affinity list' with a specific verb and resource. It details the types of fields returned (list-specific, global, enriched), effectively distinguishing it from siblings like affinity_get_field_values which retrieves field values rather than definitions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when you need the schema of fields for a list but does not explicitly state when to use this tool versus alternatives or provide exclusions. It lacks guidance on when not to use it, leaving the agent to infer based on purpose alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations (readOnlyHint, etc.) are consistent; description adds specific return fields and constraints (no field data), going beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences including a code block; purpose first, then returns, then important note. No extraneous text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a simple get-by-ID tool: explains purpose, return format, limitations, and points to the right tool for more data.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with good descriptions; the description adds return format context (JSON example) but doesn't significantly enhance parameter meaning beyond schema baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Get a single opportunity by ID from Affinity CRM' with explicit resource, action, and identifier. Return fields listed, distinguishing from siblings like list and get_list_entries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly notes 'Returns basic opportunity info only' and directs to affinity_get_list_entries for field data, providing clear when-to-use and alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=true and destructiveHint=false, and the description adds details about being a simple GET request with a structured response. It provides comprehensive information about field types, enrichment sources, and example outputs, fully aligning with and extending the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (Use Cases, Returns, Field Value Types, Enrichment Sources, Examples) and front-loaded with the main purpose. It is somewhat lengthy but every section adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple GET tool with no required parameters and no output schema, the description is extremely complete. It covers field types, enrichment sources, response structure, and example use cases, leaving no ambiguity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single parameter (responseFormat). The description adds meaning by explaining its purpose, valid values (json/markdown), and default behavior, which is helpful beyond the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Retrieve all global (account-wide) field definitions for organizations/companies' and specifies it returns complete schema information. It distinguishes itself from sibling tools like affinity_get_persons_fields by targeting organizations specifically.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Use Cases' section lists explicit scenarios like schema discovery and form generation. It notes 'No Parameters Required' and explains the optional responseFormat parameter. While it doesn't explicitly say when not to use, the context from sibling tools makes it clear this is for schema retrieval, not field values.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, idempotentHint=true. Description adds valuable context about field types (enriched, global, relationship-intelligence) and example field IDs, enhancing transparency without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with sections for description, field types, return format, and examples. Front-loaded with key purpose, and every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description provides a complete return JSON example, covers all parameters, and explains field types. Adequate for a simple get-by-ID operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all parameters (100% coverage), baseline 3. Description adds meaningful examples (field IDs), categorization of fieldTypes, and context for personId (where to find IDs), exceeding baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Get a single person by ID from Affinity CRM' and distinguishes from sibling tools like affinity_list_persons (list) and affinity_create_person (create). The specific verb 'get' and resource 'person by ID' make the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description implies use when a specific person's details are needed, but lacks explicit when-not or alternatives. Sibling tools exist (e.g., affinity_search_persons), but no guidance on choosing between them is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds value by explaining it is a simple GET request, detailing the response structure (field types, enrichment sources), and mentioning the API version limitation. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (purpose, use cases, response format, field types, examples). It is somewhat lengthy but every section adds necessary information. It front-loads the main purpose and is appropriately sized for a schema discovery tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (one optional parameter, no required params, no output schema), the description covers all necessary context: purpose, usage scenarios, response structure with examples, and even API version limitations. It is fully complete for an AI agent to select and use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with the single parameter responseFormat fully defined. The description adds context by explaining its purpose (choose output format), default value ('json'), and concrete use. This exceeds the baseline of 3 for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies 'retrieve all global (account-wide) field definitions for persons' with a clear verb and resource. It distinguishes from siblings like affinity_list_persons and affinity_get_organizations_fields by focusing on field schema retrieval, and it highlights that this V1 endpoint is not available in V2.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description lists extensive use cases (schema discovery, form generation, field validation, etc.) and provides example scenarios. However, it does not explicitly state when to avoid using this tool or compare it directly to alternatives like affinity_get_field_values or affinity_get_organizations_fields.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only and idempotent. The description adds meaningful context: returns array with strength scores (0.0-1.0), explains the strength scale, and notes potential data sparsity. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with sections (version note, use case, parameters, returns, limitations, example). Front-loaded with core purpose. Every sentence contributes, no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description fully explains return type and strength interpretation. All limitations are listed. Given the tool's complexity and lack of output schema, the description is complete and actionable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds substantial value: explains required/optional status, default and max for page_size, and details the return value with strength ranges. Helps agent understand parameter impact.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it discovers team connections to an external contact for warm introductions, with a specific use case example. It distinguishes from sibling tools like affinity_search_persons by focusing on relationship strengths.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use (warm introductions), limitations (cannot query by organization, one external person at a time), and version note (V1 not V2). Provides clear guidance on alternative actions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, idempotent, non-destructive. Description adds context: returns error if no Status field, not all lists have swimlanes. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured: definition, explanation, parameters, example JSON, use cases, note. Slightly redundant with schema but each section adds value. Not overly verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, but full JSON example compensates. Covers return structure, use cases, error condition. For a simple retrieval tool with annotations, it is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. Description repeats listId info and does not add extra meaning for responseFormat beyond schema. No new semantic value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Get pipeline stages (swimlanes) for an Affinity list.' Explains what swimlanes are and their relation to the Status field, differentiating from sibling tools like affinity_get_list_fields.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides three specific use cases and notes error conditions and that not all lists have swimlanes. Lacks explicit alternatives or when-not-to-use, but sufficient for guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive. Description adds crucial behavioral details: no text filtering, pagination with max 100 per request, field types (enriched, global), and example return fields. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with clear sections (Important Notes, Returns JSON example, Example enriched fields). Every sentence adds value, no fluff. Concisely covers all essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description provides a complete JSON return structure with example and covers all parameters, behavior, limitations, and pagination. Fully sufficient for an AI agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions. Description adds significant value beyond schema: explains fieldTypes categories, pagination cursor usage, limit default and max, responseFormat options, and provides example enriched field names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists companies from Affinity CRM and explicitly distinguishes from siblings by noting it does not support text/name filtering, directing users to affinity_get_list_entries for searching.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use (listing companies) and when-not-to-use (text/name filtering), with clear alternative (Saved Views via affinity_get_list_entries). Also notes pagination and parameter usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

In addition to annotations (readOnlyHint true, idempotentHint true), the description explains it's a V2 beta endpoint, details the return structure (HTML content, creator, timestamps), pagination, and note types. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with sections for Parameters, Returns, Note Types, and Example, front-loading the purpose. While somewhat lengthy, each section adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 100% schema coverage for 4 parameters, annotations present, and no output schema, the description adequately explains pagination, note types, and provides an example. It lacks error handling or rate limit info but is sufficient for the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds minor context (companyId source, cursor from previous response, limit defaults) but omits the responseFormat parameter present in the schema, reducing value beyond what schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List all notes attached to a specific company in Affinity', specifying the verb (list), resource (notes), and scope (specific company). This distinguishes it from sibling tools like affinity_add_note and affinity_list_person_notes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context on what the tool returns and includes an example, but it does not explicitly state when not to use or compare with alternatives. However, the tool's name and context make its purpose clear among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds detailed JSON output structure, pagination behavior, and notes on response format, providing comprehensive behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured: clear first sentence, explanatory paragraph, code block for output, and relevant notes. While thorough, it is slightly verbose but not wasteful, earning a 4.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description provides a complete output structure, pagination details, and cross-references to related tools. It fully equips an agent to use this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with parameter descriptions already detailed (e.g., limit default/max, cursor format). The description does not add new parameter-level information, only reinforces existing schema details, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get all lists in Affinity CRM' with a specific verb and resource. It distinguishes from sibling tools like affinity_get_list (single list) and mentions related tools for fields and entries.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context that lists are spreadsheet-like collections and includes notes on next steps (get fields, get entries). It implicitly differentiates from single-list retrieval tools, but lacks explicit when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds that only basic info is returned, includes pagination structure, and notes that opportunities belong to opportunity-type lists. This adds meaningful context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-organized with sections, but slightly lengthy. All content is relevant and adds value. It could be marginally more concise, but still effective.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, but description includes a JSON example with all fields (data, count, hasMore, nextCursor, summary). It explains limitations and linking to other tools. Combined with annotations, it is fairly complete for a list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear parameter descriptions (e.g., ids example, limit range). The description does not add additional parameter meaning, but the schema itself is sufficient. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List opportunities from Affinity CRM' and defines opportunities as deals/fundraising leads. It distinguishes from sibling tools like affinity_get_opportunity (single) and affinity_get_list_entries (field data).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells when to use this tool (basic info) and when to use affinity_get_list_entries for field data. It provides an example workflow, making selection effortless.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnly, non-destructive, idempotent behavior. The description adds important context: V2 BETA status, HTML content in notes, creator info, timestamps, and note types. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is well-structured with sections for parameters, returns, note types, and use cases. It is somewhat lengthy but not wasteful. Front-loaded with the main action. Minor verbosity prevents a top score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Since no output schema is provided, the description compensates fully with a detailed JSON response structure, note type explanations, pagination details, and use cases. Covers all necessary context for an agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 100% coverage with descriptions. The description repeats parameter info and adds sourcing context for opportunityId, but does not explain the responseFormat enum distinction. Baseline score of 3 is appropriate with minor extra value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists notes attached to a specific opportunity, differentiating it from similar note-listing tools for companies and persons. It uses specific verb-resource pairing and identifies the parent object.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains where to get the opportunityId (from other tools) and lists use cases, but does not explicitly contrast with siblings like affinity_list_company_notes or affinity_list_person_notes. Some implicit differentiation but lacks explicit when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, idempotent, open-world. The description adds value by detailing the response structure, note types, and that notes from meetings/emails are included if interaction info is present. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (purpose, parameters, returns, note types, example). It is slightly verbose but each section adds necessary information. No wasted words; could be slightly shorter but efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a list tool with no output schema, the description compensates by providing a full JSON response example, pagination details, and note type semantics. It covers the key aspects needed for correct usage, though error handling or rate limits are missing (not expected for this tool).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (baseline 3). The description adds extra context for personId (source), cursor (from previous response), and limit (default and max). It does not mention the responseFormat parameter, but the schema covers it. Overall, meaningful added value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists notes for a specific person and details the resource and action. It includes note types and an example. However, it does not explicitly differentiate from sibling tools like affinity_list_company_notes, which slightly reduces clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context on how to use parameters (e.g., personId from other tools) and explains note types, but lacks explicit guidance on when to use this tool versus alternatives. No exclusions or when-not-to-use are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, idempotent behavior. Description adds important behavioral details: no text filtering, max 100 results per request, and field types. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with clear sections (overview, notes, returns, field lists). Every part adds value, though slightly lengthy. Front-loaded with main purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Comprehensive: covers desired functionality, limitations, pagination, field choices, and provides a sample response. No output schema but description compensates with JSON example and field lists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions. Description adds extra value by listing the exact enriched and relationship-intelligence fields, and explaining the type parameter's meaning ('internal' vs 'external').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists persons from Affinity CRM and distinguishes from siblings by noting it does not support text filtering, unlike search tools, and provides alternatives like using 'ids' or saved views.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when not to use (no text/name filtering) and provides alternatives: use 'ids' for known persons or affinity_get_list_entries for saved views. Also explains pagination and type field meaning.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false. Description adds valuable context: V1 endpoint, exact/partial matching, empty term behavior, global vs custom organization semantics. No contradiction. Add more about authorization or rate limits? Not needed given annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured: purpose, V1 note, use cases, behavior, parameter list, return JSON, examples. Every section adds value, front-loaded with purpose. No fluff. Ideal length for a search tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, but description provides full return JSON. Explains pagination, global flag semantics. Missing explanation of withInteractionPersons/withOpportunities in description text, but schema covers them. Nearly complete given complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions. Description adds context for key parameters (term matching, pageSize max, pageToken usage) and shows return structure. Two parameters (withInteractionPersons, withOpportunities) are only in schema, but that's acceptable; description complements well.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches for companies by name or domain, with specific verb 'search' and resource 'companies'. It differentiates from siblings like affinity_list_companies (list all) and affinity_get_company (by ID) by noting this is the search endpoint and mentioning V1 vs V2.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly lists three use cases: find by domain, search by name, list all. Provides example uses. Does not explicitly say when not to use, but sibling tools for creating/modifying imply this is read-only. Could be improved with direct exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds significant behavioral context beyond the annotations (readOnlyHint, idempotentHint, etc.), including partial domain matching for emails, partial name matching, empty term behavior, pagination details, and the meaning of the 'type' field (0=external, 1=internal). It does not repeat or contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (Search Behavior, Parameters, Returns) and front-loads the core purpose. It includes a full JSON example that is helpful given the lack of an output schema. Every sentence adds value, but it is slightly verbose with the example and parameter list.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (8 parameters, no output schema, many sibling tools), the description covers essential aspects: search behavior, parameter details, pagination, return format with example, and use cases. It explains the type field and interaction dates. However, it does not elaborate on withInteractionPersons or withOpportunities beyond the schema, nor does it mention the openWorldHint implications.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

While the input schema has 100% description coverage, the description enriches parameter semantics by explaining behavioral details (e.g., 'Partial domain matching works' for term, 'Omit to list all persons'). It also maps parameters to use cases in the examples, adding value beyond the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Search for persons (contacts) in Affinity by email, first name, or last name.' It specifies the verb (Search), resource (persons/contacts), and how it differs from related tools like affinity_get_person by supporting partial matching and listing all persons when no term is provided.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit use cases: find by email, search by name, list all persons. It gives example scenarios like 'Look up person by email before creating' and 'Find all persons at a company.' However, it does not explicitly state when not to use it or compare it directly with sibling tools like affinity_get_person or affinity_list_persons.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint, destructiveHint, idempotentHint, and openWorldHint. The description adds behavioral context by detailing the JSON return structure (user, tenant, permissions, summary) and example use cases, enhancing transparency without contradicting annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a clear purpose, usage guidance, return format, and examples. It is concise and front-loads key information, though the JSON example adds length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters and informative annotations, the description provides a complete picture of the tool's behavior, including return structure and example usage. It is sufficient for an agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No input parameters exist, and schema coverage is 100%. The baseline of 3 applies as the description adds no parameter information, but the lack of parameters makes this dimension neutral.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: verifying authentication and retrieving current user info, organization details, and API key permissions. It uses specific verbs and distinguishes from sibling tools, which are focused on data manipulation or retrieval of specific entities.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly recommends using the tool to confirm API key working status and check access, with concrete examples. While it does not explicitly list when not to use, the context and sibling tools make the appropriate usage clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.