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

Annotations already establish the read-only safety profile, and the description adds real behavioral context beyond them: it reads the currently published version only, must be re-read after publish, returns { items, next }, and each item's key-vs-label rule for prefill is stated explicitly. This goes well past what structured fields 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: purpose first, then the routing instruction, then the return shape. Every clause carries information (usage line, options key-not-label, matrix rows/columns) and none is filler.

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?

With no output schema, the description fully compensates by describing the return envelope and item shape, including the edge case of option questions and matrices. An agent has everything needed to call and consume it.

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?

There is a single parameter (formId) with 100% schema description coverage that already tells the agent where to get the id. The description's detail about prefill/context and option keys concerns the returned fields rather than the input parameter, so it adds little meaning to the parameter itself; baseline 3 applies.

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 and resource ('List the field keys a request can address on a published form') plus the distinguishing scope (addressable keys, value types, option keys, prefill vs context). It is clearly separable from siblings like form_get or request_create.

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 explicit when-to-use ('Call this before request_create instead of guessing keys from question titles') and a concrete re-use trigger ('re-read it after form_publish'). No alternatives are left to inference.

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