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

Annotations show a non-read-only, non-destructive write, and the description adds real detail beyond that: a CSV is written to workspace exports, the returned link works for 24 hours without signing in, rows count against the plan's daily export allowance, and per-source caps (1,000/part, 200, 1,000, 500/part) are disclosed. Quota and expiry behavior go well past what the annotations convey.

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?

Single front-loaded paragraph that leads with the plan gate and output behavior before the source catalog. Density is high and nothing reads as filler, though the long run-on source enumeration is harder to scan than a short list.

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 carries the return-value burden and does so (download link, 24h validity, remaining allowance). Combined with prerequisites, quotas, and pagination semantics, an agent has everything needed to invoke this correctly for a 4-parameter, nested-object tool.

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 baseline is 3, but the description adds genuine meaning: it explains cursor round-tripping ('pass next_cursor back as cursor') for the paginated sources, defines what each `source` value returns, and ties `prospects` to the find_prospects argument shape. Meaningful value on top of an already well-documented 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?

States a specific verb and resource ('Export a list as CSV') and then enumerates the four exact sources (edition_exhibitors, edition_sponsors, prospects, reveals), which maps directly to the `source` enum. An agent can distinguish this from siblings like list_edition_exhibitors or find_prospects without opening any schema.

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?

Prerequisites are explicit (Pro plan, 'atlas.reveal' permission, personal connection) and each source is described with its condition (prospects mirrors find_prospects args; reveals is Team plan and up and unavailable when contacts are kept out of AI conversations). It does not, however, explicitly tell the agent when to export vs. use the sibling list/read tools that return the same data.

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