record_evidence

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

With no annotations supplied, the description carries the full burden. It implicitly discloses a write/mutation ('Add evidence') and a strong fidelity constraint about content, which is genuinely useful. It says nothing about persistence, deduplication, ordering, or whether repeated calls with the same source accumulate — meaningful gaps for a recording 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?

Two short sentences with zero waste: the purpose is front-loaded and the critical fidelity constraint follows immediately. Nothing is padded or repeated from the 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 and annotations are absent, so the description's job is mainly to define intent and constraints, which it does well for a simple two-parameter tool. The unresolved format of 'source' and the lack of any note on how recorded evidence is stored or later used are the remaining 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 must compensate. It adds real meaning for 'content' — verbatim source text, never a summary — but leaves 'source' undefined (URL, tool name, file path, free-form label?). Half the parameters remain semantically underspecified.

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 names a specific action and resource — 'Add evidence by hand' — and clarifies with a parenthetical example (text from a non-proxied, non-hooked tool). This distinguishes it from the verification-oriented siblings (verify_claim, verify_answer), though it never names those siblings explicitly.

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 gives a concrete usage condition — when the source tool is not proxied or hooked, i.e. manual capture is the only path — plus an operational rule to pass the exact source text rather than a paraphrase. It does not state when NOT to use it or route to a specific alternative sibling, so it falls short of a 5.

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