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

Annotations cover readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint. Description adds constraint details: method only GET (other values raise), write methods blocked, write guidance to preview+execute_approved, untrusted ERP content warning, and return-shape variance. However, it does not cover rate limits or auth requirements beyond allowlist, so slight gap but strong overall.

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?

Front-loads the critical 'LAST-RESORT' judgment, then usage guidance, then args and returns. Some sentences are dense and the tool-name list is long, but every part serves selection or invocation: no filler. Slightly heavy for a strict 5 but well-structured and appropriately sized.

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?

Given the tool's complexity (generic API gateway, allowlist, write-block safety, untrusted content) and 0% schema coverage, the description supplies endpoint, params, return-shape, and safety constraints. Output schema exists (so return details needn't be fully described), but correlation_id is not mentioned. Overall complete for safe use, minor gap only.

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 0%, so the description has to carry param meaning. It does: endpoint path examples and allowlist validation, method restriction, params syntax (query string or JSON, max 4096 chars), required properties for collection reads, count/single/sub-path exemptions, and key list with -gte/-lte normalization. Missing correlation_id detail, but the rest is thorough.

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 gives a specific verb+resource ('generic GET for allowlisted weclapp API reads') and explicitly positions the tool as last-resort with named alternatives (search_entities, get_entity, verify_purchase_invoice, etc.). This clearly distinguishes it from siblings.

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?

Explicit when-to-use conditions ('field/filter combination no first-class tool exposes, an allowlisted entity without a dedicated tool, narrow properties projection') and when-not-to-use ('Never for writes, downloads'). Names specific alternative tools and states that using execute_api for those domains is a tool-selection error.

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