post-crm-v3-objects-line_items-search_search

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It notes that a body parameter is required, which is a key invocation requirement, but it fails to disclose whether the operation is read-only, what the response shape is, or any pagination/limiting behavior (despite these being in the schema). The example provides some structural insight but not behavioral expectations beyond the request format.

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 concise and front-loaded with the endpoint and requirement, followed by a useful example. The example is slightly verbose but directly aids usage. There is no filler or repetition of every schema detail. It earns its place by clarifying the required body structure.

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 is sufficient to initiate a search call with the provided example, but it lacks important context such as the response format (no output schema provided) and any notes on pagination or property selection beyond the schema. Given the absence of annotations, the description only partially compensates for missing structured context, leaving the agent to infer return values and edge cases.

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 schema covers all parameters with descriptions, so the baseline is 3. The description adds significant value by specifying that parameters must be wrapped in a `body` object (e.g., `{body: {...}}`), which is not apparent from the schema's flat properties. It also gives a concrete example showing how to compose filterGroups and properties, clarifying the intended use of these parameters beyond their schema descriptions.

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 identifies the operation as a POST to the line_items search endpoint and clarifies that it requires a body with search criteria. It clearly refers to searching line items, which distinguishes it from search endpoints for other object types (quotes, invoices) among the siblings. However, it does not explicitly state 'search line items' in prose, relying on the endpoint path.

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 provides a concrete example of how to structure the body, which implies usage for searching with filterGroups and properties. But it gives no explicit guidance on when to use this tool versus alternatives like batch-read or get endpoints, nor any exclusions or recommended scenarios. The example is the only usage signal, but 'when' context is missing.

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