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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower. The description still adds real behavioral context: it uses only supplied input, it always includes the status quo and 'doing nothing' cards, and it closes with self-critique of what would sharpen the map. It does not specify length or format of the output beyond 'cards'.

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 organized as purpose, inputs, outputs — a sensible front-load. Some phrasing is loose ('Helps you decide what buyers compare you with'), but no sentence is filler and nothing important is buried.

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?

There is no output schema, so the description carries the return-value burden, and it does enumerate what comes back (per-competitor cards, status quo, doing nothing, lead areas, discovery questions, sector questions and objections). What remains unclear is the shape and size of that output, which matters for a generative tool with six inputs.

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 all six parameters, including the sector enum and the bracket-note convention for competitor names. The description only restates that competitors, weaknesses, and strengths are optional, adding little semantic detail beyond the schema.

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 states a concrete outcome: it maps what buyers compare your product with and where you can lead, and it enumerates the returned artifacts (one card per competitor, status quo, doing nothing, discovery questions). The verb+resource is clear enough to act on, though it never names or contrasts itself with the sibling impact_* framework tools.

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 is implied by the input recipe (give your product, category, and optionally competitors/strengths/weaknesses), which signals the situation it fits. There is no explicit when-to-use versus when-not, and no routing to alternatives such as impact_anchor_market or impact_full_audit.

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