run_cpm

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

Annotations already convey read-only, idempotent, and non-destructive behavior. The description adds meaningful transparency about the algorithm's scope, including forward/backward passes, lag types, calendars, constraints, data date, retained logic, and progress overrides. It also explains what result is produced and how to interpret differences.

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 a single long sentence but front-loads the core action and packs useful detail without obvious filler. It could be split into more digestible sentences, but every clause contributes meaningful information about behavior, output, or interpretation.

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?

The description thoroughly explains the tool's purpose and output categories, but it omits any guidance on the required path parameter or the optional limit/project parameters. Since there is no output schema, the agent is also left without a precise return format, making the definition incomplete for fully 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 0%, and the description provides no explanation for any of the three parameters: path, limit, or project. An agent cannot infer what 'limit' or 'project' mean or how they affect execution. The description entirely fails to compensate for the missing schema-level parameter documentation.

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 states a specific action ('Run the server's own CPM engine') and a concrete resource, then details what the pass includes and what outputs are reported. It also distinguishes itself from sibling tools like critical_path by emphasizing a full engine run plus a comparison against saved float/early dates.

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 context: the tool is for validating or investigating discrepancies between a recomputed CPM result and the scheduling tool's saved values. It explains that differences may indicate settings, calendars, or stale files, but it does not explicitly name alternatives or state when not to use this tool.

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