Change History

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

Beyond the annotations (readOnlyHint=true, destructiveHint=false, etc.), the description adds substantial behavioral detail: it returns a JSON array, page/per_page control pagination and response reports remaining pages, project_id defaults to the config value, and failures return error payloads with specific HTTP statuses (401, 403, 404). It also explicitly reaffirms 'Read-only — it changes nothing,' which is consistent with annotations and adds clarity for the agent.

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 concise and well-structured, with each sentence serving a distinct purpose: purpose, usage, default behavior, return format, read-only note, error handling, required parameters, and API reference. While the final two sentences about Procore API category and endpoint may be slightly redundant for an agent already aware of the MCP context, they add useful reference information and do not bloat the description.

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 no output schema, the description compensates by explaining the return format ('JSON array of change histories'), pagination behavior, error payloads with common HTTP statuses, and read-only nature. It also covers the required parameter (project_id) and default configuration behavior. This is comprehensive for a read-only list/lookup tool and leaves little ambiguity for the agent.

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?

The schema already provides 100% coverage with descriptions for all 4 parameters, giving a baseline of 3. The description adds extra semantics: it explains that project_id defaults to the value set by procore_set_config when omitted, and that page/per_page control pagination with the response reporting remaining pages. This goes beyond the schema's basic field names and types.

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 it is 'Change history for timecard entries,' identifying the specific resource and scope. It also explains the tool's purpose: 'Use this to discover change histories or to look up the id of one before calling a tool that needs it.' This distinguishes it from sibling history tools for other resources (e.g., list_change_history_project, show_timecard_entry_change_history_company).

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 explicitly says when to use the tool ('Use this to discover change histories or to look up the id of one before calling a tool that needs it'), providing clear usage context. It does not explicitly list alternative tools or when-not-to-use scenarios, but the mention of 'timecard entries' implies scope and the siblings make the differentiation obvious.

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