review_case

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

Annotations already cover read-only and non-destructive behavior; the description adds that the tool inspects references/facts/dates/quotes/grounds/decisions and explicitly does not validate semantic support or law. It also mentions loading a methodology topic dossier, which is extra context not present in annotations. No contradiction with annotations.

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 short sentences, with the primary action front-loaded and no filler. The second sentence is slightly awkward ('Load methodology topic dossier for the contract') and could be clearer, but overall the description is economical.

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 tool taking a large nested dossier and returning no documented output, the description is serviceable but incomplete: it states what is checked and what is excluded, but it does not describe the result format, how results are reported, or exactly what 'Load methodology topic dossier' means. These gaps matter because there is no output schema to fill them.

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?

The single `dossier` parameter has 0% schema description coverage, so the description must carry the semantic weight. It refers to the parameter as a 'structured justification' and names the components that will be checked, which helps the agent understand what shape/content matters. It doesn't enumerate every nested field, but the input schema supplies that structural detail.

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 a concrete action ('Check') and a concrete object ('a structured justification'), and it lists the specific elements it verifies (referenced pieces, facts, dates, quotes, grounds, decisions). The scope is clear enough to distinguish it from a generic or semantic analyzer, though it never names a sibling tool explicitly.

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 implies usage when a caller wants to verify the structural integrity/completeness of a case dossier, and it explicitly says it does not validate semantic support or law. However, it gives no explicit 'use when' condition and names no alternative tools, so the agent must infer how it relates to check_evidence/evaluate_rule.

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