podyx_v1_reports_metrics

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

Beyond the annotations (readOnly/idempotent/destructive=false), the description discloses genuinely useful behavior: 422 with no partial headline for typed-input, complexity and allocation-coverage errors; opaque 404s for inaccessible references; 429 analysis_busy with Retry-After: 1; and native 500/503 passthrough. That is real retry and failure-mode guidance a caller could not infer from structured fields. It is held back by the trailing 'a quote does not reserve a slot or lock a price', which is boilerplate from a quoting tool and weakens trust in the rest.

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?

It is compact but disorganized: the opening sentence fuses a verb phrase with a bare REST path, permission, error and rate-limit notes are strung together without grouping, and the final sentence about quotes locking prices has no bearing on a read-only metrics report. Content that earns its place is padded with a sentence that does not.

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?

Annotations already cover the safety profile and there is no output schema, and the description does fill in auth, error and throttling contracts. However, for a metrics report it never says what the returned metric surface contains (measures, grouping, time coverage) or resolves the pagination/filter references that conflict with an empty schema, leaving the agent without a picture of the result.

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 input schema declares zero properties with additionalProperties:false, yet the description refers to 'signed client filters' and instructs to 'follow all pagination' — neither exists as an input. With 0 params the baseline would be 4, but here the text implies parameters the agent cannot supply, which is actively misleading rather than additive.

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 the resource ('business metrics') and the backing endpoint (GET /api/v1/reports/metrics), so the agent knows it is a reporting read. But 'business metrics' is not differentiated from the many sibling reports tools (reports_summary, reports_revenue, reports_capacity, reports_customers, reports_evidence), and the opening clause 'and connected studio' is garbled enough to blur what the tool actually covers.

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?

The only gating guidance is permission-related ('Requires current reports:read', clients:read for identities), which is useful but is a prerequisite, not a when-to-use rule. Nothing tells the agent when to pick metrics over reports_summary or reports_revenue, and no exclusion or alternative is named.

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