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

Without annotations, the description carries the burden. It discloses permanent removal and associated chunks but lacks detail on authentication, rate limits, or side effects. Adequate for a simple deletion.

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: first states action and effect, second provides usage guidance. 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 one-parameter delete tool with no output schema, the description covers purpose, effect, and ID sourcing. Lacks mention of return value, but permanent removal is noted.

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 the only parameter with a description; tool description reiterates the source of the ID. Since schema coverage is 100%, description adds minimal 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 verb 'delete' and the resource 'memory/artifact', and distinguishes from siblings like memdata_list (which finds IDs) and memdata_ingest (which adds).

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 instructs to use memdata_list to find artifact IDs, providing clear context. It does not explicitly exclude any scenarios but implies caution through 'permanently removes'.

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 states the tool stores content into long-term memory but does not disclose any additional behavioral traits like limits, persistence guarantees, 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?

Two sentences, no waste. Every part contributes to purpose and usage guidance.

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 ingest tool with 2 params and no output schema, the description sufficiently covers the purpose and parameter usage. It omits return value details, but that is acceptable 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%, so the baseline is 3. The description adds value by giving examples for the 'name' parameter but does not substantially enrich 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 verb 'Ingest' and the resource 'text content into long-term memory', distinguishing it from siblings like memdata_delete, memdata_list, etc.

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 'Use this to store important information, notes, decisions, or context that should be remembered across conversations,' providing clear context but no exclusions or 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 are provided, so the description carries full burden. It reveals that the tool returns chunk counts and dates, implying it is a read-only operation. However, it does not detail the exact fields returned or its behavior under limits. Still, it provides a solid behavioral outline.

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-loads the core purpose, and provides immediate context for use. Every word adds value with 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?

Given no output schema, the description partially explains return values (chunk counts and dates). It covers the main use cases but lacks explicit field names. Considering tool complexity and sibling context, it is adequately 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% with a single well-documented parameter (limit with default and max). The description does not add extra meaning beyond the schema, 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 explicitly states 'List all stored memories/artifacts' with specific outputs ('chunk counts and dates'). It distinguishes from siblings by mentioning use cases: 'before querying' and 'to find artifact IDs for deletion', which aligns with sibling tools like memdata_query and memdata_delete.

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 this tool to see what is in memory before querying or to get IDs for deletion. It does not explicitly state when not to use it, but the positive guidance is sufficient for an agent to make appropriate choices.

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 must fully disclose behavior. It states it returns similar content with scores but does not indicate whether the tool is read-only, if it modifies data, or any prerequisites. The read-only nature is implied but not confirmed.

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 primary action, and every word adds information. 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 the tool has only 2 parameters, no output schema, and no annotations, the description covers the main functionality. However, it could mention that the output includes similarity scores, which it does, but fails to clarify the return format or pagination behavior.

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 the description adds value by providing an example for the 'query' parameter ('e.g., "What did we decide about the database?"') and specifying default and max for 'limit'. This enhances 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 uses 'search' as the verb, identifies the resource as 'memory', and specifies it returns semantically similar content with similarity scores. This distinguishes it from siblings like 'memdata_list' (listing) and 'memdata_query_timerange' (time-based).

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 for natural language search but does not explicitly state when to use this tool versus alternatives like 'memdata_query_timerange' for time-range queries or 'memdata_list' for listing. No exclusions or specific contexts are 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?

No annotations are provided, so the description carries the full burden. It conveys the core behavior (search with time range) but omits details like read-only nature, error handling, or result ordering. A brief note about safety (e.g., 'This is a read-only operation') would improve transparency.

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 (two sentences) and front-loaded with the core purpose. It avoids extraneous detail. One minor improvement: the second sentence could be integrated into the first to be even more compact.

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 (search with filters, no output schema), the description adequately covers the essential information. It clearly differentiates from sibling tools and provides usage context through examples. Missing details like result format or pagination are acceptable for a tool of this 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 all parameters well-described in the schema. The description adds no additional semantic meaning beyond the schema, such as parameter relationships or constraints (e.g., that 'since' and 'until' define a range). 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 tool's action ('Search memory') and scope ('within a specific time range'), with concrete example queries that illustrate its intended use. It effectively distinguishes itself from sibling tool 'memdata_query' by emphasizing the time range constraint.

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 example queries that imply appropriate usage scenarios (time-specific searches). However, it does not explicitly state when not to use this tool (e.g., for general searches without time constraints, use 'memdata_query') or mention 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 are provided, so the description must cover behavioral traits. It states the tool finds related entities and shows co-occurrence, but does not disclose whether it is read-only or has any side effects. Additional details on data mutation or permissions would improve transparency.

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. 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?

The tool has no output schema, and the description only vaguely mentions output as 'shows who/what appears together in the same context.' It does not describe the structure, fields, or format of the response, leaving a significant gap for a tool that likely returns a list of relationships.

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 the schema already describes each parameter. The description adds illustrative examples for the 'entity' parameter and lists example values for 'type', adding marginal 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?

The description uses a specific verb 'Find' and resource 'entities related to a person, company, or concept in your memory', clearly distinguishing it from sibling tools like memdata_query which search memory more broadly.

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 like memdata_query or memdata_list. It lacks explicit context for when relationships are more appropriate than direct querying.

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 mentions saving and storing, but does not disclose whether it overwrites previous sessions or if it is safe to call multiple times. The description is adequate but not comprehensive for a mutation 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?

The description is two short sentences, front-loading the purpose and usage. Every sentence adds value 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?

Given no output schema and no annotations, the description is nearly complete for a simple save operation. It clearly explains what is stored and when to call it, though it could mention expected behavior after calling.

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 description adds no additional meaning beyond what the schema already provides for parameters summary, working_on, and context.

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 saves a session handoff before ending, storing work summary and context for the next session. It distinguishes itself from siblings like memdata_session_start by focusing on ending a session.

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 before context compression or when ending a work session, providing clear usage context. It lacks explicit when-not-to-use guidance, but the 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?

No annotations provided, so description carries full burden. It does not disclose side effects (e.g., whether it mutates state, creates a new session, or is idempotent). Only mentions what it returns, not behavioral characteristics like safety or mutability.

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 a single sentence with emoji for visual emphasis. It is front-loaded with the call-to-action and efficiently lists what the tool returns. Every part 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 no output schema and no parameters, the description adequately lists return items (identity, handoff, activity, memory stats). It is mostly complete, though lacks details on whether multiple calls are safe or if it establishes a session context.

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 parameters exist, so schema coverage is 100% by default. The description does not need to add parameter meaning, and the baseline of 4 applies as no additional info is required.

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 to call first at session start, lists return items (identity, last handoff, recent activity, memory stats), and distinguishes from sibling tools like memdata_session_end. The verb 'CALL THIS FIRST' and resource 'session' are specific and actionable.

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 'CALL THIS FIRST at the start of every session,' providing clear context for when to use. Does not mention when not to use or alternative tools, but the directive is strong and unambiguous.

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 that the tool sets or updates identity, implying a mutation. However, it lacks details on side effects, permissions, or behavior when the identity already exists (e.g., overwrite vs. merge). This is adequate but minimal.

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 extremely concise: two sentences with no fluff. Every word adds value, focusing on the core purpose and usage.

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 (no output schema, few parameters), the description covers the essential purpose and usage. It could mention persistence or idempotency, but it is largely complete for an identity setter.

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%, with clear parameter descriptions in the schema. The tool description does not add significant meaning 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 tool's purpose: setting or updating agent identity. It uses specific verbs ('Set or update') and answers the question of what the tool does. Sibling tools focus on data operations, so this distinguishes itself well.

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 usage context ('Use this to establish who you are and your purpose'), which guides when to use. It does not explicitly state when not to use or mention alternatives, but given the distinct sibling tools, this 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?

With no annotations, the description carries full burden. It states the tool is a health check and shows connectivity and storage usage, which implies a read-only operation. However, it does not disclose any potential side effects, permissions, or rate limits. The description is adequate for a non-destructive status check.

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 just two sentences, front-loaded with the main purpose. Every word adds 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?

There is no output schema, so the description helps by mentioning what is shown (connectivity and storage usage). However, it does not specify the format or structure of the result, which could be improved for 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?

There are zero parameters, and the schema coverage is 100%. The description adds meaning by specifying the tool's output: 'API connectivity' and 'storage space used.' For a parameterless tool, this provides useful context beyond the empty 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 uses a specific verb 'check' and identifies the resource as 'health and storage usage' of the MemData account. It clearly distinguishes from sibling tools like delete, ingest, etc., which are for different 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 implies usage when you want to check API connectivity and storage usage, but it does not explicitly state when to use or avoid this tool, nor does it mention alternative tools. Given the context of siblings, the guidance is adequate but not explicit.

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