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

Adds substantial context beyond the annotations: explicit $0.05 USDC price, one-report-per-payment semantics, in-memory-only processing with no storage, retry re-sends the manifest, and hard scope limits ('never runs the tools and never queries a model'). These are exactly the traits an agent cannot infer from readOnlyHint=false / openWorldHint=true / destructiveHint=false, and nothing contradicts those hints.

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?

Front-loaded with price and the concrete output list, with the sibling contrast and scope caveats following. It is dense but every clause carries information; the only cost is a long single paragraph that an agent must parse rather than scan.

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?

With no output schema, the description compensates by enumerating what the report contains (verdict band, counted flags with evidence, per-tool rows, ordered fixes). Combined with the billing, privacy, and scope statements, an agent has everything needed to decide to call it and what it will receive.

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%, so the schema already documents the url GET caps, the accepted manifest shapes, and mutual exclusivity. The description only adds the retry implication that the manifest or its URL must be re-supplied; it adds little else about the two parameters. Baseline 3 is appropriate when the schema carries the load.

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 opening clause names the exact artifact ('one full tool-ergonomics audit report for one submitted MCP manifest') and enumerates the deliverables: verdict band, per-section counted flags, per-tool rows, ordered fix list. It explicitly contrasts with the manifest-claim audit (V6), so an agent can distinguish this from manifest_audit and its ergonomics_* siblings without opening a schema.

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 states the selection condition clearly: use this when the question is whether a model can tell a manifest's tools apart and call them from what is written, versus whether the manifest's claims are true. It also warns about the paid retry behavior causing a re-send. However, it never mentions ergonomics_precheck or ergonomics_criteria as cheaper alternatives, which is a notable omission for a paid tool sitting beside a precheck sibling.

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