Verify Claim

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

Annotations declare readOnlyHint=true, which is consistent with a verification tool. The description adds meaningful behavioral detail beyond the annotation: it discloses that the tool uses configured verifiers (SQLite/filesystem/JSON) and only rechecks 'parseable factual claims,' while showing that non-parseable claims (e.g., 'all tests pass') rely purely on tracked evidence. This granularity aids the agent in knowing what to expect.

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?

The description is a single, dense sentence that packs purpose and behavioral nuance efficiently. It's front-loaded with the primary action. Slightly verbose phrasing ('for parseable factual claims (row counts, file lines/bytes/existence, versions)') but earns its length by clarifying what counts as parseable.

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?

The tool has a nested goalContract object and 2 parameters, but the description covers the core behavior well: what gets verified, how (verifiers), and when. No output schema exists, so the description doesn't need to explain return values. Given the moderate complexity and full schema coverage, the description is reasonably complete, though it doesn't specify what passing/failing output looks like or edge cases (e.g., unconfigured verifiers).

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 100%, so both parameters are documented in the schema. The claim param example ('the row count is 1,284') and goalContract description ('use this when a worker/orchestrator/reviewer loop needs explicit done criteria') add useful meaning beyond the raw schema. This is baseline-plus credit, but the description doesn't add much more semantic depth than the schema already provides.

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 clearly states the tool's purpose: it checks whether a claim has enough tracked evidence and rechecks SQLite/filesystem/JSON verifiers for parseable factual claims. The specific verb 'check/recheck' plus the resource ('claim', 'tracked evidence') distinguishes this from siblings like require_evidence_for_claim, gate_check, and satisfy_gate, though the distinction isn't explicitly drawn.

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?

The description explains when to use it — before the agent asserts a claim — and distinguishes two cases: claims with tracked evidence, and parseable factual claims needing verifier rechecks. It does not explicitly name alternative tools or state when NOT to use it, but the context (verify claims before asserting) is reasonably clear.

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