Infimeta Public-source Search

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the agent already knows this is a non-destructive local write. The description adds the useful detail that the report is "stored privately for research," giving data-retention context, but it never states that the report is persisted/creates a record, nor whether it can be updated or duplicated.

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 filler, and the core purpose is front-loaded. The word "Optionally" is slightly ambiguous but costs little space.

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, 0% schema coverage on three parameters, and a silent mutation, the description should explain how to obtain query_id, what happens on submission, and how outcome should be chosen. None of that is present, so an agent can invoke it but not confidently.

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. It loosely maps to outcome ("whether a previous search helped") and missing ("which information is missing"), but never explains the query_id parameter's provenance or the meaning of the enum values useful/incomplete/irrelevant, leaving a third of the parameters opaque.

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 (report) and a specific payload: whether a previous search helped and what information was missing. It contrasts implicitly with the sibling search_public_sources, which performs searching rather than collecting feedback, though the distinction is not made explicit.

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?

"Optionally report" and "a previous search" imply this is post-search feedback, which gives some usage context. However, there is no explicit when-to-use versus when-not, no mention that it requires a query_id from a prior search, and no reference to the sibling tool.

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?

Adds two genuinely non-obvious behaviors: queries are recorded for research (a privacy/data-retention disclosure an agent should surface to users) and the optional purpose field has no effect on ranking. This is consistent with readOnlyHint=false and openWorldHint=true rather than contradicting them. What is missing is any note on result volume, ranking, or rate limits.

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 short sentences with the core capability front-loaded and no filler. Terseness is close to the edge — 'communities' and 'scholarly metadata' could be tighter — but every clause carries 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 4-parameter, no-output-schema search tool the description covers purpose and data-retention well but leaves the source-selection and follow-up-chaining parameters unexplained, and gives no sense of what a result set contains. Adequate but with clear gaps an agent will hit on the first non-trivial call.

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 50% schema coverage, the description compensates for one gap by clarifying that 'purpose' is a no-op for results. It says nothing about 'sources' (the enum list the agent must choose from) or 'follow_up_of' (the UUID linking semantics), both of which are undocumented in the schema as well.

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 names the concrete corpora searched (encyclopedias, scholarly metadata, communities), which tells an agent exactly what content it reaches. The negative scoping 'Not whole-web search' sharpens the boundary, but it never mentions the sibling report_search_gap or how they relate.

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?

'Not whole-web search' is an explicit when-not condition, and 'Optional purpose does not affect results' tells the agent the purpose field is not required for good results. It stops short of naming alternatives or saying when a gap should be reported instead.

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