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

Annotations already declare read-only, idempotent, non-destructive and open-world, so the safety bar is low. The description still adds real context: a 100/day-per-wallet allowance, in-memory input handling, and an explicit statement that it does not execute the server or certify its safety or honesty, which meaningfully bounds what the verdict means.

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?

Four tight sentences: the offer and rate limit come first, then inputs, then the return, then the scope disclaimer. Only 'pass caller' is slightly jargon-ish, but no sentence is redundant.

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, and the description does describe what comes back (verdict line, score, counts) plus its limits and non-goals. For a single-input, non-mutating grading tool this is close to complete; only error or failure behavior is left unstated.

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 100% and each parameter already documents its format and mutual exclusivity, so the description only needs to add framing. It contributes 'pass caller' and the free-allowance tie-in but no additional syntax or format guidance, making the baseline 3 appropriate.

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 and resource (grade an MCP server's tools/list manifest against the spec) and scopes it as a free headline check whose detail lives in the paid report. It never names its closest siblings (manifest_audit, manifest_drift_precheck), so an agent must infer which of the several manifest_* tools is the paid counterpart, but the free/paid boundary is made explicit.

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?

Implies the usage context (quick free triage; go to the paid report for per-tool evidence and fixes) but never states a when-not rule or names an alternative tool. Nothing tells the agent how this differs from manifest_drift_precheck or when to skip straight to manifest_audit.

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