cortex_review

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

With no annotations, the description carries the full burden. It does disclose one meaningful behavioral trait, that the decision output is 'advisory' (a recommendation, not an enforcement), but never says whether the call mutates state, what permissions or policy preconditions apply, or what happens when a claim fails review.

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 sentences, front-loaded with the two operating modes, and no filler. The phrase 'under the project policy' is slightly opaque but is the only mildly soft wording in an otherwise tight statement.

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 branching oneOf schema, no annotations, and an output schema. The description covers both modes and the key reference constraint, and the output schema handles return values, but the claim-review mode is described far more thinly than the decision mode, leaving an agent unsure what a claim review actually entails.

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 reported at 100%, but the description still adds genuine semantics the schema lacks: that claim/assumption references are required in substance for a decision, even though the schema defaults both arrays to empty. It also ties project_id to 'the project policy' scope.

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 two distinct modes with specific verbs and resources: 'Review a claim' and 'get an advisory decision recommendation.' This maps cleanly onto the two oneOf branches and separates it from siblings like cortex_create_claim and cortex_add_evidence, though it never explicitly names those alternatives.

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 states a real usage constraint ('A decision needs at least one claim or assumption reference') and mentions the decision is made 'under the project policy,' but gives no guidance on when to pick this tool over cortex_get_context or cortex_create_claim, and no exclusions or prerequisites.

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