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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world). The description adds genuine context beyond them: output is a draft rather than a committed ICP, win rates are deliberately not computed, and CRM data must be supplied/pulled by the user rather than fetched. It stops short of describing output structure or limits.

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?

The action and its outputs are front-loaded in the first sentence, with the limitation second. It is dense but nearly every clause carries distinct information; the only cost is a long, comma-heavy sentence that could be split for scannability.

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 must carry the return-value burden, and it does so by enumerating the artifact types the agent will receive. Combined with the explicit non-goal (no win rates), an agent knows what to expect and what follow-up work remains, though the shape/format of the draft is unspecified.

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% for all 7 parameters, so the schema already documents each field. The description gestures at the same inputs (wins, losses, market changes, current ICP) without adding syntax, format, or precedence details, so the 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 names a specific verb ('Review how your ICP should evolve') and enumerates concrete outputs: a candidate change per input, a draft updated ICP, unnamed roles, loss reasons to tag, and CRM pulls. That is far more specific than the sibling names alone, though it never explicitly distinguishes itself from icp_gap_analysis or icp_deep_dive.

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 implies the use case (reviewing recent wins/losses/market changes to evolve an ICP) and adds one boundary ('It does not compute win rates; check each candidate against your CRM'). However, no sibling alternative is named and no when-not condition is stated, so routing among the many icp_* siblings is left to inference.

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