record_grade

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

No annotations are provided, so the description carries the full behavioral burden. It implies a write operation through 'Record' and adds the constraint not to infer a validated certainty score, but it does not disclose overwrite behavior, required permissions, reviewer validation, or success/failure behavior.

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?

One front-loaded sentence with no filler. It is appropriately terse, though that terseness contributes to the completeness gap scored elsewhere.

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 six-parameter, all-required mutation with nested objects, no annotations, and no output schema, the one-sentence description leaves the agent without input expectations or validation rules. It states the purpose but not nearly enough to invoke the tool 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 0%, and the description never mentions outcome, design, down, up, reviewer_id, or rationale. With six required parameters—including two free-form nested objects—the agent must infer every field's meaning from names alone.

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 verb 'Record' and resource 'human GRADE reasoning' give a clear action, and the caveat about not inferring a validated certainty score sharpens scope. It does not explicitly distinguish itself from sibling tools such as record_risk_of_bias or assess_methodology, keeping it at 4.

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 clause 'without inferring a validated certainty score' implies this is for human-supplied GRADE reasoning rather than automated scoring. However, it names no alternatives and gives no explicit when-not-to-use guidance, so usage is only implied.

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