Search Capacities objects

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

The annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already cover the safety profile. The description adds behavioral context beyond annotations by stating the search is title-only, never searches body blocks or property values, and returns IDs/titles for get_object or relation fields. It does not contradict any annotation, and it provides meaningful limitations and output expectations.

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 two sentences long, front-loaded with the key behavior (TITLE-ONLY search), and every sentence adds value: the first states the primary capability and optional filter, the second states limitations and output usage. There is no redundancy or filler, making it highly concise and well-structured.

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 presence of an output schema and the read-only, idempotent annotations, the description adequately covers the tool's scope (title-only, optional structure filtering), exclusions (body blocks/property values), and the intended use of results (IDs/titles for get_object or relation fields). It omits minor details like result ordering or pagination, but these are not essential given the schema and the simplicity of the operation.

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%, and each parameter (query, limit, apiToken, structures) is well-documented in the schema itself. The description does not add significantly new parameter semantics—it paraphrases the 'structures' filter as 'discovered structure names or IDs' but the schema already mentions 'returned by inspect_space'; it also mentions return fields, which is not parameter-specific. Therefore, this stays at the baseline of 3 for high schema coverage.

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 identifies the tool as a title-only search for Capacities objects, which is distinct from the read/write siblings like get_object, update_object, and create_object. It also specifies the resource and the scope (TITLE-ONLY, not body blocks or property values), and states what is returned (IDs and titles) for downstream use.

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 description gives strong context for when to use this tool: it is a prerequisite step to obtain IDs/titles for get_object or relation fields, and it can be filtered by structure names/IDs. It explicitly states what it does NOT search (body blocks/property values), but it does not name an alternative tool for those cases, though no search alternative exists among the siblings.

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