ck_observability

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

Annotations already provide readOnlyHint, idempotentHint, destructiveHint. The description reinforces read-only behavior and adds extra context by listing excluded operations (e.g., benchmark execution, promotion mutation). No contradictions, and adds value beyond annotations.

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 extremely concise, consisting of two sentences. The first sentence lists all report types, and the second clarifies read-only scope. No redundant information; every word earns its place.

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 complexity of the tool (9 parameters, many enum values) and the presence of an output schema, the description adequately covers the core purpose and exclusions. It could be slightly more explicit about when to use specific report types, but overall sufficient for an agent to understand basic functionality.

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 high (89%), so the schema already documents most parameters. The description does not add parameter-level details but lists the report types, which overlap with the 'report' parameter enum. Baseline score of 3 is appropriate as the description does not significantly enhance parameter understanding beyond the schema.

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 the tool reads local observability reports, listing specific report types (sessions, loop status, problems, memory, costs, trends, evals, etc.). It also explicitly states what it does not do (no benchmark execution, draft approval, etc.), which helps distinguish it from sibling tools that perform those mutations.

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 explicit 'Read-only' statement and lists excluded operations, guiding agents not to use this tool for mutations. However, it does not explicitly contrast with specific sibling tools like ck_validate or ck_execute_code, leaving some implicit guidance. Clear context for read-only usage is given.

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