Show Workflow Instance

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial value beyond them: it confirms 'Read-only — it changes nothing in Procore,' states the return shape ('Returns a single JSON object'), and discloses detailed failure semantics with specific HTTP status codes (401 expired token, 403 no permission, 404 unresolved id). This rich behavioral context goes well beyond the structured annotations.

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 front-loaded with purpose and flows logically through usage context, prerequisite, return format, error behavior, and API endpoint—well organized for scanning. Slight redundancy exists: 'Required parameters: company_id, id' duplicates the schema's required field, and the read-only statement restates the annotation. It is denser than the leanest examples but every section earns its place.

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?

With only two fully documented parameters, a strong annotation set (readOnly, idempotent, openWorld, non-destructive), and no output schema, the description carries the necessary informational load. It covers return type, error responses with status codes, required parameters, and the API endpoint. For a simple read-only GET tool, this is complete and gives the agent everything needed for correct invocation.

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 the baseline is 3; both id and company_id already carry parameter descriptions. The description adds meaningful semantics by stating that 'id must identify an existing parent record' and directing resolution via the matching list tool first—a prerequisite not captured in the schema. The 'Required parameters' line is redundant with the schema's required array, but the added id semantics justify a 4.

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 'Get information about a Workflow Instance,' a specific verb+resource statement, and clarifies scope with 'its full field set.' The phrase 'Use this when you already know which workflow instance you want' distinguishes it from list-oriented workflow siblings, and the explicit endpoint GET /rest/v1.0/workflow_instances/{id} pins down the exact operation.

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 clear usage context—use when you already know the instance and need its complete field set—which implies list tools are for discovery. It also instructs the agent to 'resolve it with the matching list tool first,' explicitly pointing to the alternative workflow. However, it does not name a specific sibling tool or provide an explicit when-not-to-use exclusion, so it falls short of a 5.

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