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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint, so the bar is lower, yet the description adds substantial operational context: duration_class timing tiers (~2s fast, 1-5s slow, heavy may exceed gateway timeout), billing semantics (1 credit per body item), the exact error shape {error, reason, status_code, elapsed_ms, retry_hint}, and the upstream_timeout retry rationale. Minor tension: readOnlyHint=true vs POST-request bodies in the schema, but the description never claims mutation, so not a contradiction.

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 sentence one, followed by a dense but high-information second paragraph. Every clause earns its place: duration classes, concurrency, batching, billing, error format, and retry guidance — nothing is redundant. The structure moves from purpose to planning to failure handling logically.

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?

An output schema exists, so return values needn't be described. For a moderately complex proxy tool, the description covers the planning flow, performance expectations, concurrency rules, billing, error handling, and retry behavior comprehensively. The only shortfall is silence on invalid/unknown operation_id error behavior, which would strengthen guidance, and the undocumented 'fields' param noted above.

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 50%; the schema itself richly documents body, limit, and params, so the description needn't restate them. The description adds marginal param value via the '1 credit per body item' billing note tied to body. However, the 'fields' parameter has zero documentation in both the schema and the description — a genuine gap the description fails to compensate for. With mid coverage and the schema already doing heavy lifting, 3 is appropriate.

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 first sentence is a precise verb+resource+scope statement: 'Call a Sugra API endpoint by operation_id from the bundled catalog.' It clearly differentiates from siblings (describe_endpoint describes, search_endpoints searches, get_snapshot/get_timeseries fetch data), positioning call_endpoint as the executor. The scope qualifier 'from the bundled catalog' and the operation_id dependency add specificity that no sibling matches.

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?

'Plan calls with describe_endpoint's agent_hints' explicitly instructs the agent to consult a sibling tool first, which is strong cross-tool guidance. It also gives practical 'when/how' advice on batching, concurrency ('keep parallel calls within max_concurrency'), and retry strategy ('a single retry often succeeds'). It stops short of explicit exclusions (when NOT to use this tool), hence not a 5.

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