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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description corroborates ('Reads data only') while adding non-obvious context: the call is a POST despite being a pure read, and the parameter bag is free-form and report-specific. It does not describe response shape or error behavior, but the safety profile is fully covered.

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?

Three short sentences, front-loaded with purpose, then the parameter convention with an example, then the safety/endpoint note. Nothing is repeated and nothing is padding.

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 two-parameter tool with a nested free-form object and no output schema, it covers how to call it but not what the returned rows look like, nor how to obtain a valid report_id given that no sibling lists custom reports. Adequate but with a real practical gap.

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 the baseline is 3, but the description goes beyond it by exemplifying the parameter map with concrete keys and date-formatted values ({'Start': '2026-01-01', 'End': '2026-01-31'}), which the schema's generic additionalProperties constraints do not convey. It stops short of explaining which keys exist for each report.

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 ('Run one of the company's saved custom reports and return its rows'), and the notion of 'saved custom reports' cleanly separates it from every sibling, which are all get/list/create/update tools for concrete entities. An agent can identify it without opening the 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?

Usage is implied rather than stated: it tells the caller this consumes saved report definitions and report-specific key/value parameters, and gives a worked example. It does not say when to prefer it over a sibling resource list, nor where a valid report_id comes from (there is no list-reports sibling), leaving discovery to inference.

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