Bulk Update Harm Sources

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

The description goes well beyond the annotations. It discloses that company_id defaults to procore_set_config, that fields should be passed as top-level arguments (nested under 'harm_source' in the payload), that it returns the modified harm source, and specifies common failure HTTP statuses (401, 403, 404). This gives the agent a clear picture of behavioral outcomes and error handling, which annotations alone do not provide.

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 compact but information-dense. It front-loads the purpose and then efficiently covers usage preference, payload handling, default behavior, return value, error cases, required parameters, and API endpoint. Every sentence adds value without redundancy, though it is longer than strictly necessary.

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 params, no output schema, annotations present), the description is quite complete: it covers purpose, when to use, parameter behavior, default values, return value, and error scenarios. It does not mention batch size limits or what happens with invalid ids beyond 404, but these are minor gaps for a bulk update tool.

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 the baseline is 3. The description adds meaningful semantic value: it clarifies that record fields are passed as top-level arguments despite being nested in the payload, and that company_id defaults to the procore_set_config value. These details go beyond the schema's basic property descriptions, justifying a score above baseline.

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 the tool's function: 'Updates the active status for multiple harm sources in a single request.' It specifies the resource (harm sources), the action (updating active status), and the bulk scope, distinguishing it from single-record operations. The name and title also align, and the description adds 'multiple' and 'single request' context.

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 explicit usage guidance: 'Prefer this over repeated single-record calls when handling many harm sources at once.' This tells the agent when to use the tool and implies an alternative (single-record updates). However, it does not name the specific sibling tool (e.g., update_harm_source) or provide explicit exclusions for when not to use it, 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.