Record claim evidence

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

Annotations declare destructiveHint=true and idempotentHint=false, and the description earns credit by disclosing exactly what is destroyed: "Replaces the stored evidence and updates review status." It also clarifies that BYO model execution is not implemented, correcting a plausible misinterpretation of the mode parameter. It stops short of saying whether prior evidence is recoverable or what the response contains.

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 sentences, front-loaded with the action, then usage routing, then mutation semantics, then signal meaning. Slight redundancy with the schema on signal enumeration and quote length, but no filler.

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 destructive mutation with no output schema, the description covers the write effect, the status side effect, the research division of labor, and the meaning of the payload. The only gap is the shape of the confirmation/return, which is minor given the review-status update is named.

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 the baseline is 3; the description adds value by explaining that signals express support/contradiction/mixed/inconclusive rather than truth, and that BYO model execution is unimplemented — a stronger statement than the schema's narrower "this field alone does not run a provider model." Claim ID and quote truncation are already covered by the schema.

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 — recording agent evidence and alignment signals for an existing claim — and immediately distinguishes itself from get_claim (inspection) and extract_claims (prior step). An agent can identify the right tool without opening the schema.

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 explicit sequencing ("Use after extract_claims") and names the alternative with the condition that selects it ("use get_claim to inspect evidence without changing it"). It also constrains the semantic scope of signals (never a truth verdict; the user judges), which prevents misuse.

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