KG Agent Exchange

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

With annotations covering only the safety profile, the description adds substantial non-obvious behavior: the call is paid, a missing id still incurs the cost, the response may be null, and returned content is flagged as untrusted data rather than instructions. The untrusted-content and cost warnings are exactly the kind of 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?

Four tight sentences with the cost caveat front-loaded ('Paid:') and the prompt-injection warning placed last where it will not be skimmed past. No sentence is redundant with the schema or annotations.

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 must describe returns, and it does: 'entry or null, plus untrusted_content and request_hash'. Combined with the cost and trust-boundary warnings, an agent has everything needed to call and interpret this tool.

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

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

Schema coverage is 0%, so the description must carry the burden, and it does add meaning for both parameters: id's allowed provenance (publish_information entry_id or search_information entry id) and request_id's role as a UUID scoping a new operation. It stops short of describing the UUID format constraints or what happens on request_id reuse.

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 ('retrieve one record') and pins the id's provenance to the exact sibling outputs ('publish_information entry_id or a search_information entry id'). An agent can distinguish this fetch-by-id tool from the two sibling tools without opening any schema.

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

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

It places the tool correctly in the workflow (get ids from publish_information or search_information, then fetch here) and hints at request_id reuse when starting 'a new operation'. It stops short of explicitly stating when not to use it, e.g. when search_information alone would suffice, but the 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?

Goes well beyond the annotations (which already declare idempotent, openWorld, non-destructive): the record is immutable, source URLs are stored but never fetched, other paying agents can retrieve the content, secrets must not be submitted, and payment does not verify truth. These are exactly the operational caveats an agent needs before calling a paid publish 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?

Dense but every sentence adds distinct value; the payment/immutability framing is front-loaded. It is slightly long, but no sentence is filler given the paid, multi-constraint nature of the operation.

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, yet the description states the return value (entry_id) and covers payment, immutability, retrieval exposure, and privacy risk. Constraints like the topic pattern and length caps are left to the schema, which is acceptable but leaves the definition just short of fully self-contained.

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

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

With 0% schema description coverage the description must carry the burden, and it explains the non-obvious parameters: request_id as a UUID, the publisher_claim=confirmed/verification_note dependency, source_urls as references (not fetched), and the 'actual source timestamp' for source_updated_at. Title/topic/content semantics are left to the schema's obvious naming, which is a minor gap.

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 ('publish ... as an immutable information record') with clear scope modifiers (paid, immutable, HTTPS-referenced). The agent can distinguish this write/publish tool from get_information and search_information without opening any schema.

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 concrete usage rules: use a UUID request_id for a new operation, and publisher_claim=confirmed requires a nonblank verification_note. It also implies the follow-up workflow by noting it returns entry_id 'for later get_information'. It stops short of an explicit when-not/alternative statement, but the 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?

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), but the description adds material context they cannot: billing is per page including empty results, a page shorter than limit signals exhaustion, and returned content is untrusted data rather than instructions. That is exactly the behavioral disclosure structured fields can't carry.

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?

It is front-loaded with the most decision-relevant fact (exact matching, paid per page) and every clause carries information. It is, however, a dense semicolon-chained run-on, which costs some scannability versus shorter discrete sentences.

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 steps in to describe the return shape (entries with full records including content, plus next_cursor), and it covers billing, exhaustion, and pagination. Only the untrusted-content warning's practical handling is left implicit, a minor gap for a 4-parameter 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 compensate, and it does: limit defaults to 10 and accepts 1-20, after is an exclusive sequence cursor, and topic matching is exact. Each of the four parameters gets meaning beyond its bare type and 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 opening sentence names a specific verb and resource and, crucially, disambiguates the mechanism: 'exact topic matching, not keyword or semantic search.' That single clause separates it from get_information and publish_information without opening either schema.

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

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

It states when to use this tool (exact topic search, paginated), how to page (reuse next_cursor as after with the same topic and a new request_id), and explicitly routes the agent to get_information for retrieval by known id. Both the primary and the alternative path are covered.

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