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

Goes well beyond the annotations: states the free-tier quota (100/day per wallet), that submitted content is processed in memory only, that the audit never executes the tools and never queries a model, and that grading is limited to measurable document properties. These are exactly the side-effect and trust facts an agent needs before sending a manifest.

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?

Three front-loaded sentences: offer and quota first, then inputs and outputs, then the free/paid boundary and grading limits. Every clause carries information; nothing is repeated from the schema verbatim beyond necessary naming.

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, but the description explicitly names the four returned counts, so an agent knows the return shape. Combined with quota, input modes, and the explicit statement of what the audit does not do, there is no material gap for a three-parameter read-only tool.

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 'url', 'caller', and 'manifest' are already fully documented including the mutual exclusion. The description restates the same facts (manifest shapes, pass caller, URL alternative) without adding format or validation detail beyond the schema. Baseline 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 gives a specific verb+resource ('headline ergonomics check of an MCP tool manifest') and enumerates exactly what comes back: tool count, definition-token total, flagged-pair count, undescribed-parameter count. It distinguishes itself functionally from the paid tier ('the paid report'), but never names the sibling tool (ergonomics_audit) that an agent should pick when the headline counts are insufficient.

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?

Clear usage context: submit a manifest object or a manifest URL, and pass 'caller' to key the free allowance. It also implies the when-not case by pointing at 'the paid report' for verdict bands, evidence, and fixes. No explicit named alternative or prerequisite caveat beyond the quota, so it stops short of a 5.

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