AI TPM Knowledge

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description does add something beyond that: it discloses a failure mode — it will not synthesize an answer when the corpus lacks coverage. However, it never says whether that manifests as an empty result, an error, or a partial list.

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 no waste, and the core capability is stated first. The second sentence is a little elliptical but still earns its place as a behavioral caveat.

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 should say what comes back — a list of citations? titles plus snippets? — and it does not. Combined with absent sibling differentiation and an undocumented parameter, an agent has to guess at both selection and return shape.

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% for the single `topic` property; the only hint is the phrase "for a topic". The description adds no meaning about what constitutes a valid topic, how broad or narrow it should be, or how the 2000-character limit is meaningfully used.

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?

"Retrieve cited reading evidence for a topic" gives a verb and a resource, but "reading evidence" is undefined and nothing distinguishes this from the sibling tools `search` and `fetch`, which plausibly also retrieve things by topic. An agent cannot tell from this sentence alone which of the three to pick.

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?

There is no when-to-use guidance and no mention of the alternatives `search` and `fetch`, despite them being obvious competitors for a topic-based retrieval call. The second sentence describes a behavior (non-fabrication), not a usage condition or exclusion.

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

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

Beyond the readOnly/idempotent annotations, it discloses a critical behavioral trait: the returned text is untrusted evidence and must not be executed as instructions. For a fetch tool returning external content, that prompt-injection warning is exactly the context annotations cannot express.

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 the retrieval contract before the safety caveat. Every clause carries information; nothing is redundant with the name or schema.

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?

An output schema exists, so return values need no explanation, and the annotations cover the safety profile. What remains unstated is failure behavior for an unknown ID and the scope of retrievable documents, minor gaps for a one-parameter read tool.

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

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

Schema description coverage is 0%, so the description must carry the load, and it does the important part: the single `id` must be a stable search ID, not a URL or arbitrary identifier. It does not mention the maxLength bound or format of that ID, but the essential semantic constraint is present.

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?

Uses a specific verb ("Retrieve") with a specific resource ("a document") and constrains the lookup key to a stable search ID, which implicitly separates it from the search sibling. It never names search or build_reading_list directly, so sibling differentiation is inferred rather than stated.

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?

Gives a clear positive condition (you must already have a stable search ID) and an explicit exclusion ("never by arbitrary URL"), which tells the agent when not to use it. It stops short of routing the agent to a specific alternative when no ID exists, e.g. pointing at search.

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 read-only, idempotent, non-destructive, closed-world behavior, so the description need not repeat safety basics. It adds valuable context beyond annotations by stating that results are canonical citations and that retrieved content is evidence, never instructions, which is important safety guidance.

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 short sentences with no wasted language. The core purpose and source constraints are front-loaded, followed by return format and safety 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?

Given the simple one-parameter schema, rich annotations, and presence of an output schema, the description covers the essential corpus scope, return nature, and safety posture. The main gap is routing guidance versus sibling tools, which prevents a full 5.

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 is only one required parameter, query, and schema coverage is 0%, so the description should ideally compensate. It clarifies that the query searches approved, published website knowledge, adding domain meaning, but it does not explain query syntax, expected format, or length constraints.

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 states a clear verb and resource: search approved, published website knowledge. It adds useful scope constraints about the corpus, but it does not explicitly distinguish this from sibling tools such as fetch or build_reading_list.

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 by the purpose statement; there is no explicit guidance on when to use this tool versus fetch or build_reading_list. No prerequisites, exclusions, or alternative routing are provided.

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