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

Annotations only declare readOnlyHint=true, so the description carries most of the behavioral burden and does so well: zero credit cost, a hard 5000-row cap with a truncated=true flag, the days default of 2 and 365 max, and the fact that the caller must write the output file. It stops short of describing ordering, pagination, or how truncation interacts with limit.

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?

Dense but front-loaded: the row/column shape comes first, then the schema-drift field groupings, then cost, then the days/cap mechanics. The canonical-vs-deprecated field enumeration is verbose but is genuine information an agent needs to interpret returned columns, so it earns its place.

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 still conveys the return shape (one row per contact, engagement columns, action grid vs. lossy compatibility view, canonical icp_score vs. deprecated fields), plus the truncation flag and row cap. Nothing an agent needs to interpret or bound the result set is missing.

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 0%, so the description must compensate and largely does: `days` is documented as filtering by discovery date with a default of 2 and max 365, and `limit` is documented as requesting fewer rows than the cap. `limit`'s interaction with truncated is only implied, keeping this below 5.

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 and resource with scope: 'Export warm leads as structured rows (one row per contact; engagement columns show the most recent engagement).' The 'YOU write the CSV/file from the returned rows' clause clarifies what the tool does NOT do, implicitly separating it from a file-producing or list-paging sibling, but it never names list_warm_leads or get_warm_lead_detail, so sibling differentiation is left to inference.

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?

The description gives operational context (free, costs no credits; days defaults to 2, set explicitly for a longer window) which tells an agent how to call it, but never says when to prefer export_leads over list_warm_leads or get_warm_lead_detail. Usage is implied by 'export' vs 'list' rather than stated.

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