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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description reinforces the closed-world trait in plain language: "works only from what you give and looks nothing up." It also discloses non-obvious output behavior — ties are reported as ties, budget is expressed as the observed ACV range, and sector notes appear only when a supported sector is named — which an agent could not infer from schema or annotations.

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 the payoff and then input, output, and the closed-world caveat. Every sentence carries information, with only mild density in the long output sentence listing ties, budget, recommendations, and sector notes.

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 and all five parameters optional, the description carries the burden of describing return values, and it does so without needing to restate field syntax. Minor gap: it does not state what happens if customers is empty or whether one input mode is preferred when both are supplied.

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 slightly beyond by enumerating the customer attributes in the order the schema defines them and by framing customers and customer_descriptions as alternative input modes rather than separate fields. It also signals that business_model can be inferred from other inputs, matching the schema note.

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 the outcome ("decide which customers to go after next") and the mechanism (derive shared patterns from your best customers), plus what is returned: shared patterns, ties, budget range, recommendations, sector notes. It is clearly a pattern-extraction/ICP tool rather than a scoring or prioritization tool, though it never names the near-neighbor siblings like icp_scoring_model or lookalike_signal_generator to draw the boundary explicitly.

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 gives concrete input guidance — supply customers either as a structured list with the seven named attributes or "in your own words" — which is real usage steering. It does not say when to prefer this over icp_gap_analysis, icp_scoring_model, or account_prioritization, so tool selection among 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.