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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower. The description adds genuinely new context: the full column set returned, the whole-CRM default (a size/scope warning), and that the operation is Free, which is cost information no annotation conveys.

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 tight sentences: output shape first, then the three input modes, with the no-argument default front-loaded before the convenience note. No filler.

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 nine optional params, no required fields, and no output schema, the description carries the return-value burden and does so via the column list. Minor gap: nothing about size limits or truncation behavior on a whole-CRM export, which matters for a 1000-item maxItems lead_ids 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 67%, and the description compensates by explaining the lead_ids path, delegating filter semantics to list_crm_leads ('the same filters as'), and defining the omit-all default. It does not enumerate individual filters like tag/stage/has_email, but the delegation note keeps it understandable.

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 (Export) and resource (Creator CRM creators) and enumerates the exact CSV columns, so the agent knows both the action and the output shape. It is clearly distinct from list_crm_leads (read/list, not export) and from the generic export_csv sibling, which does not mention CRM creators.

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?

Explicitly gives two selection modes — pass lead_ids, or the same filters as list_crm_leads — and states the default: omit everything to export the whole CRM. It lacks an explicit exclusion versus the sibling export_csv, so the agent still has to infer which export tool to pick.

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