form_fetch_customized_form

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

Annotations already flag this as a non-read-only, non-idempotent, open-world POST, so the agent knows there may be side effects. The description adds the important fallback detail that a form is generated when none exists, which explains the non-read-only hint. It does not say whether a generated form is persisted, what permissions are required, or whether repeated calls produce different results.

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-loaded with the core behavior, which is good. But the first and second sentences restate the same fetch idea, and the trailing raw endpoint URL adds little for an agent selecting a tool. Tightening to two sentences would lose nothing.

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 POST with no output schema and a deeply nested JSON-schema body, the description covers the essential contract: lookup by search parameters, generation from a supplied schema as fallback. The remaining gaps—return shape, whether generation persists, which params are required for which path—are moderate but not blocking.

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 five parameters (body, formId, formType, sourceId, sourceType) are already documented. The description only loosely gestures at 'search parameters' and 'the JsonSchema' without adding format, precedence, or which parameters matter for the lookup versus the generation path. Baseline 3 applies when the schema carries the load.

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: fetch a request form, or generate one from a JSON schema if none is persisted. The dual fetch-or-generate behavior distinguishes it from the nearby form_fetch_form and form_generate siblings without naming them. Slightly diluted by the endpoint URL restatement, but the purpose is unmistakable.

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 conditional 'generate one if there isn't a persisted form' implies when the fallback kicks in, which is real usage guidance. However, it never says when to pick this over form_fetch_form or form_generate, or what search parameters must match, leaving selection between siblings to inference.

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