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

Annotations already establish readOnly/idempotent/closed-world safety, so the description is free to spend its words on what annotations can't say — and it does: coverage is derived from each product's public site, and a missing feature means 'not marketed,' not 'not built.' That provenance and interpretive caveat materially change how an agent reads the results.

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 sentences, front-loaded with what the tool returns, then the caveat, then the parameter tip. Every sentence carries information and none is filler; slightly dense with clauses in sentence one but no redundancy.

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 structure needn't be described; the description still conveys grouping and column semantics. Combined with annotations covering safety, what remains omitted — pagination/volume behavior on a full catalog matrix, and the fixed enum list for category, which lives only in the schema — is minor.

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%, so the baseline is 3. The description goes beyond the schema's terse 'only return features where coverage differs across the set' by spelling out the semantic outcome — rows where everyone or no one has it are hidden — which clarifies what 'differs' means operationally.

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+resource (get the feature matrix for your competitive set) and enumerates the row/column content: canonical features grouped by category, competitor coverage, and your own coverage. It does not name a sibling to contrast with — notably outmano_get_feature_gaps, which an agent could easily confuse with this — so it is clear but not sibling-differentiated.

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?

Usage guidance is present but only at the parameter level: 'Use differences_only to hide rows where everyone (or no one) has it' tells the agent when to flip the flag. There is no statement of when to call this tool versus outmano_get_feature_gaps or the battlecard tool, and no prerequisites are given.

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