Delete Harm Source

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

The description contradicts the idempotentHint annotation by stating 'a repeat call returns 404,' which is inconsistent with idempotent behavior. While it adds useful disclosure about permanence and error statuses, the contradiction with annotations is a serious issue that makes the description unreliable for behavioral expectations.

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 the main purpose and includes useful specifics (permanence, error statuses, endpoint). However, it has redundancy such as repeating the id-resolution guidance twice and stating required parameters that are already in the schema. Still, it's reasonably organized and not excessively verbose.

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?

Covers many important aspects: restriction on Procore-provided harm sources, prerequisites, permanence, repeat-call behavior, and common error statuses. But the internal contradiction about company_id and the conflicting idempotentHint reduce completeness. No output schema exists, so return value on success is not described, but the description is otherwise fairly complete.

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 description doesn't need to explain parameters, but it introduces a contradiction: it says 'company_id defaults to the value set by procore_set_config when omitted' while the schema marks company_id as required and the description later says 'Required parameters: company_id, id.' The guidance for id (resolve with list tool) is helpful but the company_id inconsistency lowers the score.

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 'Deletes a custom harm source,' which is a specific verb+resource combination. It clearly distinguishes from siblings like list_harm_sources, create_harm_source, show_harm_source, and update_harm_source, and adds 'custom' to exclude Procore-provided harm sources.

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 explicit prerequisites: confirm the target id with the matching show or list tool, and resolve the id with the matching list tool. It also states a clear exclusion ('Procore-provided harm sources cannot be deleted'). However, it doesn't name specific sibling tools, and the guidance is more about prerequisites than when to prefer this over alternatives.

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