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

No annotations are provided, so the description carries the full burden. It does a good job disclosing behavioral constraints for check_config (required keys, conditional compare_to, target_path requirement). However, it does not disclose whether the update is a merge or replacement of existing fields, any potential destructive effects, or authorization requirements. This leaves the mutation semantics incomplete.

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 dense but well-structured, front-loading the purpose ('Update a metric') and then using a compact list of per-kind requirements. It minimizes waste and organizes complex information effectively, though it could benefit from bullet points or clearer separation of the general update behavior from check_config specifics.

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 (7 parameters, nested objects, no output schema), the description is incomplete. It provides deep coverage of check_config but omits guidance on other metric fields (name, rubric_bands) and the llm_judge metric type. It also does not describe the return value or side effects, leaving the agent with partial understanding for a tool that can update more than just check_config.

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%, so the description must add meaning. It thoroughly explains the check_config object, including per-kind required keys, compare_to behavior, and target_path/expected_path semantics, which goes well beyond the schema. However, it does not cover top-level parameters like name, instruction, or rubric_bands, leaving them without semantic elaboration.

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 'Update a metric' which is a specific verb+resource that distinguishes it from create/get/list/delete siblings. However, it does not explicitly mention the full scope of updatable fields (e.g., name, instruction, rubric_bands), instead focusing almost entirely on check_config, which slightly narrows the apparent purpose.

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 provides conditional guidance for using different check kinds ('For a deterministic check set metric_type...') and how to use compare_to with expected. However, it does not explicitly state when to use this tool over alternatives like metrics_create, nor does it provide exclusions. The usage context is implied but not fully articulated.

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