model_config_get

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

No annotations are provided, so the description carries full burden. It discloses that model discovery is auto-derived from local CC transcripts (a useful behavioral detail), that the default comes from a settings file, and that usage is aggregated over N days. However, it does not mention whether this is read-only, whether it makes external calls, or performance characteristics. The detail about behavior is substantive for a pure read/inspection tool.

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?

Single dense sentence with parenthetical asides. The parenthetical commentary like 'the models you actually used' and 'how much fable vs opus the fleet burned' adds flavor and domain context but borders on unnecessary flourish. Well front-loaded with the verb 'Get' and clear components, though slightly verbose for what could be more compact.

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?

An output schema exists, so return-value detail is not required in the description. The tool's three-part return is thoroughly enumerated. The only gap is that behavioral safety (read-only nature) is not explicitly stated, but with an output schema present, the context is largely sufficient for a config inspection tool.

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% — usage_days has a complete description (aggregation window, default 7, max 90). The description's reference to 'last N days' and 'over the last N days' reinforces but does not add meaningfully beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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 three things this tool returns: available models (auto-discovered), current default startup model, and per-model workflow agent usage over a time window. The verb 'get' and resource 'model governance state' are specific and unambiguous. The sibling tool model_config_set clearly complements it (get vs set), making differentiation natural.

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 implies this is a read/config-inspection tool but does not state when to use it vs alternatives. However, model_config_set is the obvious sibling and the read-vs-write distinction is largely implied by the name. No explicit when-not-to-use guidance is given for the usage_days window bounds (max 90 in schema).

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