bdesign_canvas_search

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

The readOnlyHint annotation already covers the non-destructive nature. The description adds that it searches by specified fields but discloses no other behavioral details such as result limits, ordering, pagination, or whether it searches all projects or just one. With the annotation present, the safety aspect is transparent; only additional runtime behavior is missing.

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 description is a single, concise sentence with no redundant wording. It conveys the core purpose and search criteria efficiently.

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?

The description tells agents what the tool does and what can be searched, but it does not describe the return value or output shape. Given the absence of an output schema, this omission leaves some ambiguity about whether the result is a list, a count, or id-only matches. It is adequate for a simple search tool but not fully complete.

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?

The description clarifies the meaning of 'query' by listing name, prompt, result text, and model, and maps 'kind' and 'type' to node categories and media types. However, projectId is not mentioned at all, and there is no explicit field-to-parameter mapping. The enum values for kind and type already provide some semantics, but the description does not fully cover all parameters.

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 clearly states a specific verb ('Search') and object ('Canvas nodes') and enumerates the search dimensions (name, prompt, result text, model, kind, media type). It distinguishes itself from sibling tools like canvas_get and asset_list by focusing on searching Canvas nodes, though it does not explicitly name sibling tools.

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?

No explicit guidance is provided for when to use this tool versus alternatives such as canvas_get, canvas_view, or asset_list. The phrase 'Search Canvas nodes' implies a retrieval use case, but there is no stated condition like 'use when you need to find nodes matching criteria' or 'use instead of listing all assets'.

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