Export ai tracking evidence

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

Annotations already establish the safety profile (readOnlyHint=true, openWorldHint=false, destructiveHint=false), so the bar is lower. The description adds genuine but vague behavioral context — that results carry original provenance, may be in "partial states," and include "cost uncertainty" — which usefully signals incomplete/approximate data, though it never explains pagination, page-size behavior, or what a partial state means operationally.

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?

A single front-loaded sentence with the verb leading and no filler sentences — structurally tight. It is slightly jargon-dense ("partial states," "cost uncertainty") in a way that costs clarity more than it costs length.

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?

For a five-parameter, cursor-paginated export with no output schema, the description leaves the return shape largely unexplained; the format parameter's schema text only partially compensates. Annotations cover safety, but with no output schema the description should have described what an evidence page contains. It is minimally sufficient rather than complete.

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 100%, so limit, cursor, format, run_id, and project_id are already fully documented in the schema, including the CSV-vs-JSON distinction and cursor semantics. The description adds nothing beyond the schema, so the baseline of 3 applies.

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?

It has a discernible verb+resource ("Read ... AI tracking evidence") and a scope ("project-scoped"), but the central noun "evidence" is undefined and the descriptor does not distinguish this from the many AI-tracking siblings such as get_ai_tracking_run, get_ai_tracking_history, or export_rank_history. The tangent about "original provenance, partial states, and cost uncertainty" muddies rather than sharpens what the tool yields.

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?

There is no statement of when to use this tool versus the many adjacent AI-tracking readers/exports, and no prerequisites or exclusions are given. Usage is only weakly implied by "project-scoped AI tracking evidence."

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