explain_metric

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

With no annotations, the description carries full burden. It discloses behavior: thin dictionary lookup over percentile boxes, never guesses (returns found false with message), returns specific structure, and that caveat is from a unified source. It also states the tool does not reason about players.

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 front-loaded with the main purpose. Each sentence adds value, though a bit verbose in parts. Still efficient for the information provided.

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 simplicity (one param, no annotations, but has output schema), the description is complete. It explains input, behavior, output structure (listing fields), and limitations. With output schema existing, it doesn't need to detail return values but does so briefly.

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 0% for the single parameter 'metric'. The description adds significant meaning: metric can be a schema field name or natural phrase, provides examples, and explains behavior when input is not a card metric. Fully compensates for lack of schema description.

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 defines a single card metric, its measure, and its top caveat. It specifies the resource (card metric) and action (define/explain), and distinguishes from siblings like assess_player by noting it does not reason about specific players.

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?

Explicitly provides when to use (to ground narration of a metric's meaning) and when not to (as a verdict). It notes that for player-specific questions, one should use assess_player results, suggesting an alternative.

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