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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds one genuinely new behavioral fact, the limit cap of 50 (the schema defines no maximum), but says nothing about return format, pagination, or whether fewer results exist than requested.

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 with zero waste; the primary action and ordering are front-loaded and the cap constraint follows immediately.

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-only, one-parameter tool with rich annotations and no output schema, the description covers purpose, ordering, and the cap a caller needs to call correctly. Only the relationship to the search sibling is absent.

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 0%, so the description must carry the load; it discloses the cap of 50 but omits the default (10, only visible in the schema) and any lower bound or behavior when limit is exceeded. It partially compensates for the coverage gap, so a 3 is appropriate for the single 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?

States a specific verb and resource ('List the most recent memories') plus ordering semantics ('newest first'), which distinguishes it from get_voice_memory (single retrieval) and save_voice_memory (write). However, it never names search_voice_memories, the closest sibling, so the agent must infer the browsing-vs-searching boundary on its own.

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?

Usage is only implied: 'most recent memories' suggests a browsing/recency use case, but there is no explicit when-to-use statement, no condition that routes to search_voice_memories, and no exclusions. Adequate but leaves the agent to infer the 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 already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful content scope by noting the full record includes the transcript, but says nothing about not-found behavior, permission requirements, or response size for a transcript payload.

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 front-loaded sentence with the retrieval key (UUID) at the end and no filler. Every clause 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?

No output schema exists, and the description compensates by indicating the return includes the transcript, which is the key expectation for this call. For a read-only single-parameter tool with annotations covering safety, this is nearly complete; only error/not-found behavior is unaddressed.

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 0%, so the description must compensate, and it does partially by identifying the parameter as a UUID that identifies exactly one memory. It does not state where that UUID comes from, but the format and cardinality meaning are conveyed beyond the bare 'string' 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?

States a specific verb (Get) and resource (voice memory record), and scopes it to a single memory retrieved by UUID, which clearly separates it from the sibling list/search tools. It stops short of naming those siblings explicitly, so it is clear but not fully differentiated in-text.

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?

Usage is only implied: you need a UUID, so an agent infers this is a follow-up to search_voice_memories or get_recent_memories rather than a discovery tool. There is no explicit when-to-use or when-not-to-use statement, nor any mention of how to obtain the memory_id.

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, and openWorldHint=false, so the safety profile is covered. Because there is no output schema, the description's disclosure that results pair each tag with a usage count is genuinely useful. It still omits ordering (e.g., by count), pagination, and whether empty tags appear.

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 front-loaded sentence with no filler; the verb and the result shape are both stated immediately. Every word 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?

For a zero-parameter, read-only enumeration tool with no output schema, stating what each entry contains (tag plus memory count) is close to sufficient. Minor gaps remain on ordering and whether counts reflect all memories or only the caller's, but the agent has enough to invoke it 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 tool takes zero parameters, so the baseline is 4. There is nothing for the description to clarify about inputs, and it does not attempt to invent any.

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 gives a specific verb (list) and resource (tags) plus the shape of the result ('the number of memories using each'). No sibling covers tag enumeration, so no differentiation is strictly needed. It is clear but does not explicitly distinguish itself from search_voice_memories, which may also surface tag information.

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?

Usage is only implied: an agent can infer this is the tool for discovering which tags exist before filtering by one. There is no explicit 'use this when' statement, no mention of alternatives such as search_voice_memories, and no scoping note (e.g., whether tags are global or per-user/workspace).

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=false, idempotentHint=false, and destructiveHint=false, so the write/non-destructive profile is covered. The description adds useful hard limits (character caps, 20-tag cap), but does not mention that repeated saves are non-idempotent and may create duplicates, nor what is returned.

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 very compact, front-loaded statement of purpose followed by the constraints; every clause carries information and nothing is filler. The constraint list is dense but readable.

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 4-parameter creation tool with 0% schema coverage and no output schema, the description documents all parameters, their required/optional status, and their limits. It omits duplicate-handling behavior and any indication of the returned identifier, which are minor gaps.

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 0%, so the description carries the burden and handles it well: it marks title and transcript as required and adds max-length constraints for title (200), transcript (100000), summary (2000), and tags (20 tags x 50 chars) that the schema does not express. Only the null-default nature of tags/summary is unstated.

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?

States a specific verb and resource ('Save a new memory') that clearly separates it from the read-oriented siblings (get_voice_memory, search_voice_memories, list_voice_tags). It is unambiguous what the tool does, though it never explicitly names a sibling or contrast case.

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?

Usage is only implied: the tool is the sole write operation among read siblings, so an agent can infer when to use it, but there is no explicit when/when-not guidance or mention of alternatives such as updating an existing memory instead of creating one.

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 and openWorldHint=false, so the safety profile is covered. The description adds real context beyond that: substring rather than token/fuzzy matching, result ordering (newest first), and a hard cap of 50 on limit. It omits edge behavior such as case sensitivity or empty-result handling, which keeps it from a 5.

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?

Three short sentences, front-loaded with the matching behavior and followed by returns and the limit constraint. The return-field enumeration is long but earns its place because there is no output schema; no filler sentences are present.

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?

With no output schema, the description correctly compensates by listing returned fields and ordering. For a two-parameter read tool with full annotation coverage, the remaining gaps (case sensitivity, no-match behavior, whether limit can be zero) are minor.

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 0%, so the description must carry both parameters, and it largely does: it specifies that query is a substring keyword match against four named fields, and that limit is capped at 50 (beyond the schema's default of 10). Both parameters gain meaning the schema lacks, though no format or syntax examples are given.

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?

States a specific verb+resource ('keyword search ... over title, summary, transcript and tags') and even names the matching semantics (substring). It does not distinguish itself from the sibling get_recent_memories, which is also a list-style retrieval tool, so it stops short of a 5.

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?

Usage is implied: the tool is clearly a keyword/substring search, so an agent can infer it is for finding memories by text content. However, no when-to-use condition is stated and no alternative (get_recent_memories, get_voice_memory) is named, leaving the routing decision to inference.

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