podyx_v1_reports_customers

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

Annotations already establish readOnly, idempotent, non-destructive, openWorld behavior, so the description adds genuinely new operational detail: authorization scopes, a 422 contract with 'no partial headline', opaque 404s for inaccessible references, a 429 'analysis_busy' response with Retry-After: 1, native 500/503 behavior, and a mandate to follow pagination. Some phrasing ('recorded allocation coverage errors', 'a quote does not reserve a slot or lock a price') is cryptic and its relevance to a customer report is unclear, which keeps it from a 5.

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?

The purpose is front-loaded in the first clause, which is good, but the body is a dense run of terse contract fragments ('Typed input, complexity and recorded allocation coverage errors are 422') that read like compressed API documentation rather than agent guidance. Several sentences are opaque or marginally relevant to this specific tool, diluting the useful signal.

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 complex, deeply nested reporting tool with no output schema, the description covers invocation hazards well (auth, error contracts, pagination, read-only) but never explains what the report returns — 'headline' and 'contributions' are used without definition, and no output shape is given in schema. It is enough to call the tool safely but not enough to interpret or plan around the results.

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?

The description adds no parameter-level meaning: it never mentions metric, cohort, preset, currency, client_id, date bounds, or inactivity_days. The nested schema nonetheless documents each of these fields thoroughly, so the schema carries the burden and a baseline 3 applies. The only parameter-adjacent guidance is the pagination instruction, and the top-level 'query' object itself has no description in the 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?

The opening sentence names a specific verb and resource ('Analyze studio customers') and anchors it to the underlying endpoint GET /api/v1/reports/customers. It is clearly a customer-reporting tool, but it never distinguishes itself from the many sibling report endpoints (reports_metrics, reports_revenue, reports_summary) or explains what 'customers' analysis yields versus those alternatives.

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 context is implied through permission requirements ('Requires current reports:read', 'clients:read' for identities and client_id filters) and the 'Read/preview only' note, which tells the agent this is a safe analytical read. However, there is no explicit statement of when to choose this over podyx_v1_reports_metrics or podyx_v1_list_clients, and no exclusions or prerequisites beyond scopes.

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