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

No annotations are provided, so the description carries the full burden. It discloses the tool's function (verifying references and catching typos) but does not specify behavioral traits such as whether it is read-only, requires authentication, what output format to expect, or consequences of invalid inputs. This is adequate but not detailed.

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?

Two concise sentences that front-load the purpose and include a benefit statement. No unnecessary words or 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?

The tool is simple with no output schema. The description explains the goal and result (catches typos/invalid paths) but omits details about return format, error handling, or what happens when both parameters are provided. It is adequate but not fully complete for a check 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 basic descriptions for prd_id and content. The description does not add extra meaning beyond the schema, such as how the parameters interact (e.g., mutually exclusive, both optional). Baseline score 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 the tool's purpose: verifying API endpoint references in a PRD against an OpenAPI spec. It uses a specific verb ('verify') and resource ('API endpoint references in a PRD'), and distinguishes from sibling tools like prd_create_template or prd_generate which focus on creation and generation.

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?

No explicit guidance on when to use this tool versus alternatives. The description does not mention prerequisites, mutual exclusivity of parameters (prd_id vs content), or when not to use it. Sibling tools like prd_validate might overlap, but no comparison 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?

Mentions persistent storage in ZeroDB, which is useful behavioral context. However, it does not disclose other important traits such as whether duplicates are allowed, required permissions, or potential side effects.

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?

Two concise sentences, front-loaded with purpose followed by a key behavioral detail. No wasted words.

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?

Adequately describes purpose and persistence, but lacks return value description, error handling, or behavior on duplicate names. For a creation tool with no output schema, more completeness would be beneficial.

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 each parameter described. The description adds no additional parameter semantics beyond the schema, so a baseline score of 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 the verb 'Create' and the resource 'custom PRD template', distinguishing it from sibling tools like prd_get_template (retrieval) and prd_save (saving PRDs).

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?

No guidance on when to use this tool versus alternatives, nor any prerequisites or when-not-to-use conditions. The description lacks context for an agent to decide between creating a template versus using existing ones.

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?

No annotations are provided, so the description must convey all behavioral traits. It states it fetches issue data and expands into a PRD, but does not disclose side effects (e.g., saves, overwrites), auth requirements, rate limits, or whether operations are read-only.

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 a single, front-loaded sentence that efficiently covers the core purpose and key steps with no extraneous 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?

Given no output schema, the description should clarify what is returned. It mentions expanding into a full PRD but does not specify whether it returns the PRD as text, saves to a file, or fits into the AINative platform. Also lacks guidance on error conditions or prerequisites.

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 for all parameters, so baseline is 3. The tool description adds context about using a GitHub issue but does not elaborate on parameter values or behavior beyond schema, thus meeting the 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 explicitly states 'Generate a PRD from a GitHub issue' and details the specific steps (fetching title, body, labels, comments) which clearly distinguishes it from sibling tools like prd_generate or prd_load.

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?

No explicit guidance on when to use this tool vs alternatives like prd_generate or prd_create_template. The purpose implies usage when a GitHub issue is the source, but differentiation from other PRD creation tools is absent.

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?

No annotations are provided, so the description bears full burden. It mentions auto-saving to ZeroMemory and AI context, but omits details like idempotency, overwrite behavior, permissions, cost, or whether generation is synchronous. Significant gaps remain.

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 two sentences, front-loaded with purpose, and every sentence adds value. No 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 9 parameters, no output schema, and no annotations, the description is too sparse. It does not explain return format, error handling, or how to verify completion. Missing critical context for a complex generation 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. The description adds value by noting auto-detection for ainative_services when omitted, which goes beyond the schema. Minor extra context earns a score of 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?

The description clearly states the tool generates a comprehensive PRD for AINative features, specifying the verb and resource. It distinguishes from siblings by highlighting AI platform context and automatic ZeroMemory saving.

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 use when a full PRD is needed for AINative products, but lacks explicit when-not-to-use or alternative tool references. Siblings like prd_from_issue or prd_refine are not mentioned, so guidance is implicit rather than explicit.

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?

No annotations are provided, so the description must carry the full burden. It states that the tool can 'generate or regenerate' sections, implying it may overwrite existing sections when a PRD ID is given. However, it does not explicitly disclose whether the operation is destructive, what permissions are needed, or any rate limits. The description is adequate but not thorough.

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 two sentences, with the first sentence stating the core purpose and the second providing a usage scenario. It is front-loaded and contains no unnecessary words or repetition.

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 tool has 5 parameters, no output schema, and no annotations, the description covers the basic purpose and when to use. However, it does not mention what the tool returns (e.g., the generated section text) or the behavior when no prd_id is provided. It is adequate but could provide more detail for full completeness.

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 contextual meaning beyond the schema: it clarifies that 'description' and 'product_name' are required if no prd_id is provided, and explains that prd_id provides context of the full PRD. This adds value over the raw 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 that the tool generates or regenerates a single section of a PRD. It specifies the resource (PRD section) and the action (generate/regenerate), and distinguishes itself from the sibling tool 'prd_generate' which likely handles full document generation.

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 clear context on when to use this tool: for iterative refinement of specific sections like 'Technical Architecture' or 'User Stories' without regenerating the entire document. It implies that for full document generation, one should use the sibling tool, though it does not name the alternative explicitly.

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?

No annotations are provided, so the description carries full burden. It describes the output (endpoint paths, methods, descriptions) but does not mention safety traits such as read-only nature, authentication needs, or error behavior. The verb 'Get' hints at read-only, but explicit disclosure is missing.

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 a single, front-loaded sentence that efficiently communicates the tool's purpose. Every word contributes value, with no redundancy or filler.

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 lack of output schema and annotations, the description sufficiently covers the tool's functionality: it retrieves API catalog details for a service. The single parameter is well-documented in the schema. It could mention pagination or error handling, but the core behavior is clear.

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?

The input schema already provides a clear description of the single parameter 'service' with examples. The tool description adds no additional meaning beyond what the schema offers. With 100% schema description coverage, a 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 the verb 'Get' and the resource 'API endpoint details' for a specific service or category. It distinguishes from sibling tools like prd_list_services or prd_check_api_refs by specifying that it returns endpoint paths, methods, and descriptions from the OpenAPI catalog.

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 needing API endpoint details for a specific service, but it does not explicitly mention when not to use it or suggest alternatives. Sibling tools exist (e.g., prd_check_api_refs, prd_list_services) but are not referenced, leaving the agent to infer 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?

No annotations provided, description only states basic functionality and return type. Lacks disclosure of read-only nature, error handling, or any side effects.

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?

Two sentences, no redundant words, front-loaded with action and outcome.

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?

Adequate for a simple retrieval tool but missing error behavior and explicit differentiation from similar siblings like prd_list_templates.

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 100% with examples; description adds minimal extra value by restating the parameter's purpose but does not provide constraints or formatting 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?

Clear verb 'Get' and resource 'PRD template' with specification of retrieval by name. Contrasts with sibling prd_list_templates by indicating it returns a single full Markdown template.

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?

Implied usage: use when you need a specific template's full content. No explicit guidance on when not to use or alternatives like prd_list_templates for listing.

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?

No annotations provided, so description must cover all behavioral aspects. It mentions output (unified diffs) but does not state that the tool is read-only, nor any authentication or side-effect details. For a history tool, the read-only nature is implied but not explicit.

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?

Two sentences, front-loaded with purpose, no redundant words. Efficiently conveys core functionality.

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 (one required param, no annotations, no output schema), the description covers what the tool does and what it returns. Could add notes on read-only nature or limits, but not essential.

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 one parameter. The description provides 'Artifact ID of the PRD', which duplicates the schema description. No additional meaning 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?

Description clearly states verb 'Get', resource 'version history for a PRD', and output 'unified diffs between versions'. Distinguishes from sibling tools like prd_load and prd_get_api_catalog.

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?

No explicit when-to-use or when-not-to-use guidance. Usage is implied by the description, but no alternatives or conditions 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?

With no annotations, the description carries full burden. It describes the tool as a read operation listing services, but does not disclose potential issues like empty results, pagination, or authentication requirements. Adequate but not thorough.

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?

Two sentences, one for purpose and one for usage, with no fluff. Front-loaded with key 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?

For a simple list tool with 2 optional parameters and no output schema, the description covers the purpose and usage adequately. Missing details on error handling or output format, but not critical.

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 description coverage is 100%, so baseline is 3. The description repeats the schema's parameter descriptions (verbose, category) without adding significant new context beyond their function.

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 lists AINative products/services with specific fields (descriptions, categories, etc.) and explicitly says when to use it (before writing a PRD). Distinguishes itself from siblings by focusing on services rather than templates or API refs.

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 says 'Use this before writing a PRD' which provides clear use context. However, does not mention when not to use it or alternative tools like prd_get_api_catalog or prd_list_templates, so lacks 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?

Describes it as a listing operation but lacks explicit behavioral traits like read-only nature, authentication needs, or performance impact; no annotations provided to supplement.

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?

Two concise sentences with no redundant information; efficient communication.

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 and description does not explain return format, error conditions, or usage context; incomplete for a listing 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?

Parameter description already covers semantics; tool description adds no additional meaning 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?

Clearly states listing all PRD templates (built-in and custom) with a specific verb and resource, differentiating from siblings like prd_get_template.

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?

No guidance on when to use this tool versus alternatives; no when-to-use or when-not-to-use information.

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?

With no annotations, the description carries the burden. It implies a read operation but does not disclose error handling, permissions, or return value. The description is minimal, which is adequate for a simple load but could be improved.

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?

Two succinct sentences with no wasted words. The first states the action, the second provides usage context, making it easy to scan.

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 retrieval tool with one parameter and no output schema, the description covers its purpose and when to use it. It could hint at what the returned data contains (the full PRD) to improve completeness.

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 description coverage is 100% for the single parameter. The description only reiterates the schema's info about artifact ID origin, adding no new meaning beyond what the 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 the tool loads a saved PRD by artifact ID, specifying the action and resource. It hints at its use for resuming work, which helps distinguish from sibling tools like prd_search, but does not explicitly differentiate from other retrieval tools.

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 says to use at the start of a session to resume work, providing clear context. However, it does not mention when not to use it or suggest alternative tools like prd_search for finding PRDs.

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?

With no annotations, the description carries the burden of behavioral disclosure. It mentions 'preserving version history', which is a key safety detail, but it does not specify if the action is destructive, any authorization requirements, or what happens on conflict.

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 two sentences, front-loading the purpose and adding a key behavioral detail. No wasted words.

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 tool's simplicity (3 params, no output schema, no annotations), the description covers core behavior but does not mention the return format or any prerequisites (e.g., that the PRD must exist). It is adequate but not fully comprehensive.

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 the schema already documents all parameters well. The description adds no extra meaning beyond restating that prd_id and feedback are needed, providing no additional semantic nuance.

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 action ('Refine an existing PRD') and the resource ('PRD'). The verb 'refine' and phrase 'based on feedback' distinguish it from generation or validation tools, though no explicit sibling differentiation is made.

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 feedback is available to improve a saved PRD, but it does not explicitly state when to use this tool versus alternatives like prd_generate or prd_validate, nor does it mention when not to use 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?

No annotations exist, so the description carries full burden. It discloses key traits: fast, deterministic, no AI. This adds value, but doesn't cover side effects, error handling, or authentication requirements.

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?

A single sentence that is front-loaded with the action and key distinctions. Every word contributes value, no 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?

For a simple tool with two parameters and no output schema, the description adequately covers purpose, behavior, and key constraints. It implicitly indicates the return value (rendered template) and is sufficient for most use cases.

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 minimal extra meaning beyond the schema's parameter descriptions; it reinforces that variables are for placeholder substitution and the operation is deterministic.

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 'Render' and the resource 'template', adding specific modifiers: variable substitution, no AI, pure placeholder replacement, fast, deterministic. This distinguishes it from AI-based siblings like prd_generate.

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 clear context: use for deterministic template rendering with variable substitution, and explicitly notes 'no AI' to steer away from AI-based tools. However, it doesn't explicitly name alternatives or state when not to use.

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?

With no annotations provided, the description carries the full burden. It discloses persistence, ID return, and automatic version tracking, but omits details on destructive actions, authentication needs, rate limits, or error conditions. Adequate but could be more comprehensive.

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?

Two sentences, concise and front-loaded with the core purpose, no wasted words.

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 or annotations, the description covers return value (ID) and versioning context. It could mention error handling or permissions for completeness, but for a simple save tool it is largely sufficient.

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 minimal semantic value beyond the schema: it mentions Markdown for content and gives an example for tags, but these are already implied by 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?

The description clearly states 'Save a PRD to ZeroDB as a persistent plan artifact,' specifying the action (save), resource (PRD), and destination (ZeroDB). It also mentions returning an ID for future operations, distinguishing it from sibling tools like prd_generate or prd_load.

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 implicitly indicates when to use the tool (to persist a PRD) and that version history is tracked on updates. However, it does not explicitly exclude use cases or mention alternatives, which would be helpful but is not a major gap.

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?

No annotations are provided, so the description carries the full burden. It discloses the scoring criteria and implies a non-destructive read operation, but does not explicitly confirm idempotence, authorization needs, or side effects.

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?

A single sentence that is efficient and front-loaded. It conveys the key action and criteria without unnecessary words, though it could be more terse.

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 is provided, and the description does not specify the return format (e.g., integer score vs. breakdown). The tool has two parameters with ambiguous usage, and no guidance on expected input. Given the complexity of scoring and multiple sibling tools, more detail is needed.

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?

Both parameters have descriptions in the schema (100% coverage), so baseline is 3. The tool description adds no additional context about how prd_id and content relate (e.g., exclusive or, precedence). It merely restates the scoring criteria without clarifying parameter usage.

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 action ('Score'), the resource ('PRD'), and the output ('completeness from 0-100'). It also lists the scoring criteria (section coverage, content quality, AINative integration depth), which distinguishes it from sibling tools like prd_validate or prd_check_api_refs.

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 no guidance on when to use this tool versus alternatives such as prd_validate or prd_check_api_refs. It does not mention prerequisites, context, or 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?

No annotations provided, so the description must supply behavioral context. It explains the search is semantic and accepts natural language, but does not disclose read-only behavior, result format, or potential delays. Adequate for a simple search tool, but lacks depth.

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?

Two concise sentences that immediately convey purpose and query capabilities. No extraneous information; front-loaded for quick agent scanning.

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 tool's simplicity (3 params, no output schema), the description covers core functionality well. However, it omits details about the result format (e.g., list of PRD IDs or full text) and does not mention pagination behavior beyond the limit parameter. Minor gaps for an agent.

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% (all parameters described). The description adds context about searching across all saved PRDs and natural language queries, but does not significantly enhance parameter understanding 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 tool performs 'Semantic search across all saved PRDs' and specifies searchable criteria (topic, service name, feature description, natural language). It distinguishes from sibling tools like prd_check_api_refs or prd_validate, and even from other search tools (skill_search) by explicitly targeting PRDs.

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?

No guidance on when to use this tool versus alternatives like skill_search or other PRD tools. The description does not mention prerequisites, limitations, or when not to use 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?

With no annotations, the description carries the full burden of behavioral disclosure. It states the tool returns recommendations with justifications, which is adequate, but does not disclose whether it uses AI, calls external APIs, or has any side effects. It is neither contradictory nor highly informative.

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 a single, front-loaded sentence that conveys the core functionality without any extraneous information. Every word earns its place, and it is appropriately concise.

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 tool has three parameters and no output schema, the description is somewhat incomplete. It does not specify the format of the returned stack or justifications, which would help the agent use the response. The description is minimal but covers the basic function.

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 each parameter described. The description does not add significant meaning beyond the schema; it summarizes the usage but does not elaborate on how 'features' or 'constraints' are processed. Baseline of 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 the tool's purpose: given requirements, suggest a technology stack of AINative services, APIs, and SDKs with justifications. It uses a specific verb ('suggest') and resource ('technology stack'), and differentiates from sibling tools like prd_generate (which generates PRDs) and prd_check_api_refs (which checks API references).

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 does not provide any guidance on when to use this tool versus alternatives. There is no mention of prerequisites, situations where it is appropriate, or when to use sibling tools like prd_check_api_refs or prd_generate instead.

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?

With no annotations, the description carries full burden. It fails to clarify whether the tool is read-only, requires permissions, or reports results. The behavioral scope (checks performed) is stated, but side effects, idempotency, or response characteristics are omitted.

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?

Single, front-loaded sentence that efficiently communicates the purpose and key checks. Every part adds value, with no redundant or filler content.

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?

Missing output schema and no description of return format (e.g., pass/fail, issue list). Does not clarify that either prd_id or content must be provided. For a validation tool, these gaps reduce completeness.

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 with descriptions (100% coverage). The tool's description adds high-level context about validation areas but does not enhance parameter understanding beyond what the schema provides. 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?

Description clearly states the tool validates a PRD against quality rules and AINative constraints, listing specific checks (sections, completeness, service references, architecture). This verb+resource combination is distinct from siblings like prd_score or prd_check_api_refs, which have different focuses.

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?

No explicit guidance on when to use this tool versus alternatives (e.g., prd_score, prd_check_api_refs). The description does not mention prerequisites, conditions for use, or when not to use it, leaving the agent without decision support.

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?

No annotations provided, so description carries burden. It clearly indicates read-only operation (get content) with no destructive hints. It could mention that it does not modify anything, but overall sufficient.

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?

Two sentences, front-loaded with action and resource, no redundant 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?

For a simple read tool with 2 parameters and no output schema, the description adequately explains what it returns and its purpose. Could specify output format, but not necessary.

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 minimal value beyond schema: only reinforces that 'skill' is slug/name and 'with_references' fetches reference content.

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 uses specific verb 'Get' and resource 'skill', clearly distinguishing it from siblings like skill_list and skill_get_reference.

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 clear usage context: 'Use this to load a skill before doing the work it describes.' However, it does not explicitly state when not to use or mention sibling 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?

No annotations provided; description implies read-only retrieval but does not detail side effects, permissions, or return format. Adequate for a simple read operation.

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?

Two short sentences, every word serves a purpose. No redundancy or filler.

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?

Adequately covers purpose and usage for a simple retrieval tool. Could mention return format, but not essential given no 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% with descriptions for both parameters. Description adds an example but no additional semantic value 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?

Clearly states 'Get a single reference file for a skill' with an example, and distinguishes from siblings like skill_get by specifying it loads on-demand from SKILL.md.

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 usage context: 'when the SKILL.md says to.' Lacks explicit when-not-to-use or alternatives, but context is 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?

With no annotations provided, the description carries the full burden. It explains that skills are pulled live from GitHub and lists the return fields. It does not discuss authentication or rate limits, but for a read-only list tool on a public repo, this is adequate.

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 three sentences, front-loaded with the main purpose, and contains no fluff. 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 that there is no output schema, the description provides complete information about the output structure (name, slug, description, trigger phrases, reference files) and the source (GitHub repo). It also explains the caching behavior via the refresh parameter.

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?

The input schema has full coverage of the single parameter 'refresh' with its own description. The tool description adds context about bypassing cache and live fetching, but does not add new semantic meaning 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 that the tool lists all Agent Skills from the skills repo. It specifies the default repo, what each entry includes (name, slug, description with trigger phrases, reference files), and distinguishes from siblings by advising to call this first before applying a skill.

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 advises to 'Call this first to discover which skills exist before applying one,' providing clear context for when to use the tool. It does not explicitly state when not to use it, but the sibling tools imply alternatives like skill_get for specific skills.

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?

With no annotations provided, the description carries full burden. It discloses the dual-mode operation (ZeroDB mirror vs keyword fallback) and the prerequisite (skill_sync). It does not detail rate limits or error handling, but the behavior is sufficiently transparent for a search tool.

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 two sentences long, front-loaded with the purpose, and contains no unnecessary words. It is efficient and easy to parse.

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 lack of output schema and annotations, the description adequately covers the tool's purpose, input parameters, and behavioral modes. It could be more complete by mentioning return format or error cases, but it is sufficient for a search 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 the description adds no additional parameter meaning beyond what is already in the schema. The example query ('automate my content workflow') provides context, but overall the description does not significantly enhance parameter understanding.

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 'semantic search across all skills to find the right one for a task' and provides an example query, distinguishing it from sibling tools like skill_list and skill_get.

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 when to use the tool (finding a skill for a task) and mentions the prerequisite of running skill_sync for optimal results. It implies the fallback behavior but does not explicitly state when not to use it or direct users to alternative tools.

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?

No annotations are provided, so the description must disclose behavioral traits. It mentions refreshing the cache and that GitHub is source of truth, suggesting overwriting, but it lacks explicit details on idempotency, authentication needs, or potential side effects.

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 concise with two sentences. It front-loads the main action and then provides the constraint on syncing all or one skill, with no wasted words.

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 tool with one optional parameter and no output schema, the description is complete. It covers the purpose, data source, behavior, and parameter usage sufficiently for the agent to select and invoke 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?

The schema has 100% coverage, with a description for the optional skill parameter. The description adds value by explaining the difference between syncing all skills vs one by slug, reinforcing the schema's intent.

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: mirror skills from GitHub to ZeroDB for semantic search and offline serving. It distinguishes itself from sibling read/search tools by specifying it is a refresh operation that syncs all or one skill.

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 when to use (to refresh the cache) and that GitHub is the source of truth. It does not explicitly state when not to use or compare to alternatives, but context signals provide enough differentiation from siblings.

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