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

Annotations already cover read-only, idempotent, non-destructive and closed-world, but the description adds the human-in-the-loop semantics that annotations cannot express: it flags rather than acts, and explicitly 'never rejects'. That is meaningful context about what the tool will and won't do. It stops short of describing output shape or threshold/confidence 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?

A single dense sentence with the action front-loaded, followed by the behavioral guarantee. No filler, and the most decision-relevant facts (what it detects, that it only flags) come first.

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?

No output schema exists, so the description carries more of the return-value burden; it tells the agent the result is a human-facing flag but not the structure or severity levels. For a two-parameter detection tool with full annotation coverage, this is nearly complete but leaves the agent guessing at the response shape.

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 100% and both parameters are documented in the schema, so the baseline is 3. The description's mention of invisible characters loosely corresponds to the hidden_segments parameter but adds no format or usage detail beyond what 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?

States a specific verb (check/detect) on a specific resource (resume text) and enumerates exactly what it looks for: prompt injection ('ignore previous instructions'), invisible characters, and keyword stuffing. This clearly distinguishes it from siblings like triage_resumes and check_identity_risk, which handle routing and identity rather than adversarial content.

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 a clear when-to-use condition ('before any AI reads it') and states the downstream behavior ('Flags for a human; never rejects'). It does not explicitly name the alternative tools or state when NOT to use it, but the timing guidance is strong enough to route the agent correctly.

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