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

Annotations already declare readOnlyHint=false, idempotentHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is known, and nothing in the description contradicts it. The description adds useful scope about what gets scanned and what comes back, but omits the most consequential behavioral fact: this is a priced job submission requiring a quote_id and authorization, which the agent only discovers from the schema.

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?

Purpose is front-loaded, followed by usage, exclusion, then examples, which is a sensible order. The four example requests largely restate the preceding sentences and could be trimmed to one or two without losing routing signal.

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?

An output schema exists, so return values need not be explained, and the scan scope is well covered. However, for a priced multi-file submission tool with a required quote_id and authorized_by, the description gives no hint of the quote-then-submit workflow, leaving the agent to infer the job lifecycle entirely from the schema.

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 75%, so the schema already documents each parameter thoroughly, including quote_id and accepted_price semantics. The description maps onto the three nested inputs (manifest, config, source) but adds no format, size or syntax detail beyond what the schema states, so the baseline of 3 applies.

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 specific verb (Audit) and resource (dependency manifest, configuration and source) and enumerates what is detected: leaked secrets, dangerous patterns and unpinned dependencies, plus the outputs (risk score and grade). It is unmistakable what the tool does, though it never names the nearest sibling (submit_dependency_vulnerability_triage, submit_requirements_pin_check, submit_env_file_check) that an agent must choose between.

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 gives a clear positive trigger ('Before shipping or reviewing a project, for a fast consolidated security triage') and an explicit exclusion ('Do not choose this when you need exploitability confirmed by running the code or a CVE database'). The gap is that the exclusion describes a capability class rather than pointing at the concrete alternative tool, which matters given a sibling set containing several overlapping security scanners.

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