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

Goes well beyond the readOnlyHint annotation: it discloses the four-outcome answer space, that Boosthis chooses the comparison window and ignores one named in the sentence, and—unusually candid—that it only catches about one in six wrong claims and never catches vague ones. This is exactly the limitation context an agent needs to weigh the result.

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?

Front-loaded with the core purpose before qualifications, and each sentence carries information (outcomes, window rule, accuracy ceiling). The trailing 'Read-only' restates the readOnlyHint annotation and is the one piece of waste.

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 compensates by enumerating the four verdict values, and both parameters are fully described in the schema. Accuracy limits, window behavior, and read-only status are all covered, leaving nothing an agent needs in order to call it correctly.

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 100%, so the 240-character limit, credential refusal, and the account_token AI-allowance cost are already documented. The description adds only the window-handling note, which reads more as tool behavior than as parameter guidance, so the baseline 3 applies.

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 precise verb+resource: it holds a proposed sentence against what the running app actually did, and enumerates the four exact verdicts it can return. The scope is unambiguous and clearly distinct from sibling checks like release_check or verify_kit_install.

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 ('a sentence an assistant is about to say'), i.e. call it before asserting a claim. The limitation notes ('catches only a minority of wrong claims', 'a vague claim is never caught') help the agent judge when the call is worthwhile, but no explicit when-not conditions or alternative tools are named.

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