log_search

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

Annotations already declare a non-read-only, non-idempotent, non-destructive write. The description adds the deduplication purpose, which is genuinely useful context. However, it does not say what happens when an already-logged query is submitted again (rejected? appended?) — a meaningful gap given idempotentHint=false.

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 with the purpose front-loaded, followed by the one non-obvious parameter hint and the mandatory usage rule. Little waste; the parenthetical example is compact and useful.

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 five parameters at 0% schema coverage and no output schema, the description should explain the fields and the logging semantics. It covers only one parameter and omits what 'promoted' or 'analysis_id' mean and what the tool returns, leaving real gaps for a write 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 parameter meaning, but it only explains subquestion as a label like 'Q2'. analysis_id, query, hits, and especially 'promoted' are left entirely unexplained in both schema and description.

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: record search results into an objective's search log, with the stated rationale of preventing re-searching already-covered questions. It also implicitly distinguishes itself from paper_search as the logging companion, though the 'objective' concept is not tied to any visible field (the schema uses analysis_id).

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 an explicit trigger: 'always record after running paper_search' — a clear, actionable when-to-use rule with the relevant sibling named. It does not say what to do on failure or whether repeated logging of the same query is allowed, but the core guidance is unambiguous.

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