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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine context beyond them: what the caller receives back (a CSV plus an app_url) and what scope applies when lead_ids is omitted. It says nothing about export size limits or the uid/URL mismatch constraint documented in the schema.

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?

Two sentences, no filler, and the output shape is front-loaded ahead of the default-scope rule. Nothing here repeats the title verbatim or wastes tokens.

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 six optional parameters, 83% schema coverage, no output schema and no nested objects, the description is close to sufficient: it covers what is returned and the default filter scope. The remaining gap is sibling disambiguation against export_crm_csv, which the description never addresses.

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 83%, so the baseline is 3. The description goes beyond the schema for the one undocumented parameter, lead_ids, explaining that omitting it exports the entire kept-lead set for the conversation. It adds no meaning for conversation_id, preferences_mode, or agent_preferences, which is acceptable because those are already documented.

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+resource ('Return a CSV of kept leads') and even states the return shape (CSV plus app_url for table review/export). It does not, however, distinguish itself from the sibling 'export_crm_csv', which an agent must otherwise infer from the name alone.

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?

'Omit lead_ids to export all kept leads in the MCP conversation' is a useful default-scope rule, and 'table review/export' hints at the use case. But there is no explicit when-to-use/when-not guidance and no routing between this tool and export_crm_csv, list_leads, or export of CRM records.

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