Bulk Update Harm Sources

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

Annotations already indicate readOnlyHint=false, destructiveHint=false, and openWorldHint=true. The description adds value by clarifying partial update behavior ('only the supplied fields are changed') and stating that the modified object is returned on success. This provides behavioral context beyond the annotations, but does not reveal potential side effects, error scenarios, or authentication requirements beyond company_id.

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 three sentences long and generally concise. However, the second sentence redundantly repeats the purpose and introduces an inconsistency (Incidents vs Harm Sources). The third sentence provides Procore API metadata that may not be essential for an AI agent. It could be more streamlined.

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 has no output schema and moderate complexity (3 parameters), the description covers basic purpose, partial update, and required parameter but fails to clarify the relationship between Harm Sources and Incidents (the description mentions Incidents in a confusing way). It also omits error handling, rate limits, or what happens if invalid IDs are provided. The ambiguity about the resource being updated reduces completeness.

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 mentions company_id as required but does not elaborate on the semantics of 'ids' or 'active' beyond what the schema already provides. The phrase 'only the supplied fields are changed' implies the body fields are optional, but no additional parameter-specific details are given.

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?

Clearly states it updates multiple Harm Sources in one request. The name 'bulk_update_harm_sources' and title 'Bulk Update Harm Sources' align. However, the description confusingly references 'Incidents' instead of Harm Sources, which could mislead an agent about the exact resource being updated. This slight inconsistency prevents a perfect score.

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?

Provides minimal guidance on when to use this tool vs alternatives. It mentions partial update behavior ('only the supplied fields are changed') and required parameter company_id, but does not specify when a single update tool would be preferable or contrast with other bulk update tools. The API endpoint and Procore section are more developmental context than usage guidance.

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