Update A Manual Hold

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses partial-update behavior, return value ('Returns the modified manual hold on success'), and error semantics with specific HTTP status codes (401, 403, 404). This gives the agent a clear model of what happens on success and failure, exceeding the annotation baseline.

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 dense yet well-structured: purpose first, then usage semantics, parameter defaults, return/error behaviors, required parameters, and API context. Every sentence adds critical information without repetition or fluff, and the front-loaded purpose ensures quick recognition.

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 tool's complexity (3 required params, no output schema), the description covers all necessary aspects: what is updated, partial-update behavior, parameter defaults and resolution, return value, error payloads with common status codes, and the API endpoint. The absence of an output schema is compensated by explicitly stating the success return. This is complete for an agent to invoke correctly.

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 coverage is 100%, so baseline is 3. The description adds valuable context: project_id falls back to the procore_set_config value, and id must be resolved from an existing record via a list tool. It also clarifies that omitted fields are preserved, which directly informs parameter use. However, it does not fully correct the schema's misleading description of id as an 'Invoices resource' identifier, though the description's wording implies the manual hold ID.

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 opens with 'Update a manual hold with the ID specified in the URL,' clearly stating the verb (update), resource (manual hold), and scope (specific ID). It implicitly distinguishes from sibling list/create tools by focusing on modification of an existing record, and later specifies the HTTP method and endpoint, removing ambiguity.

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 concrete usage guidance: 'Send only the fields you intend to change; omitted fields keep their current values' clarifies partial-update semantics, and 'resolve it with the matching list tool first' directs the agent to fetch the ID. It also explains project_id defaulting via procore_set_config. It does not explicitly state when to avoid this tool, but the guidance is sufficient for typical selection.

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