get_app_analytics_performance

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

Beyond the readOnly/idempotent annotations, it discloses the plan entitlement check, the exact unpublished-site response, three named error codes with remediation hints (details.earliest, retry later, INVALID_RANGE from overlapping compare_start), and — crucially — that visitor-derived fields arrive inside `untrusted_content` and must be treated as data. That is substantial behavioral context the schema and annotations cannot convey.

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?

Dense but front-loaded: the metric definition and return shape come first, then prerequisites, then the untrusted-content warning, then errors. Every sentence carries information, though the packed error-code list in one parenthetical sentence is slightly hard to scan.

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 23-parameter, no-output-schema analytics tool, the description fully covers what is returned, the entitlement requirement, empty-data behavior, prompt-injection risk, and the error surface. An agent has everything needed to call it and interpret failures without additional context.

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 all 23 parameters are already documented in the schema; the description adds only light framing (breakdowns by country and edge location, compare period overlap). It neither explains filter interactions nor prioritizes the many optional filters, so it sits at the baseline for a fully documented 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?

States a specific verb-like resource ('Latency of the app's site in ms') and enumerates exactly what is returned: edge vs container, avg and p50-p99.9, a percentile series, breakdowns by country/edge location, slowest paths and per-path problems. That level of specificity clearly separates it from neighboring analytics tools like get_app_analytics, get_app_analytics_errors and list_app_analytics_requests.

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?

Gives concrete gating and preconditions: a plan with web analytics performance is required (else 403 PLAN_DOES_NOT_SUPPORT_WEB_ANALYTICS_PERFORMANCE), an unpublished site returns web_published: false with empty data, and it names the failure modes to expect. It does not explicitly say when to prefer this over the analytics siblings, so it falls short of the full 5.

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