Calibration report

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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false; the description independently discloses the write behavior ('resolve any that have settled since'), which is what makes this non-read-only and non-idempotent, and adds the sparsity caveat. It adds real context the annotations alone don't convey, though it doesn't say whether resolution is persisted or how it affects counts.

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?

Front-loaded purpose in the first sentence, then scoped Args and Returns sections — easy to scan. However, the Args and Returns blocks substantially restate the input schema and the existing output schema, which is mild redundancy rather than wasted length.

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?

For a two-parameter, zero-required analytics tool with both an output schema and full annotation coverage, the description is close to complete: purpose, timing caveat, parameter meaning, and result shape are all covered. The Returns block is redundant with the output schema, and the relationship to the snapshot-creation sibling is the one real omission.

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%, so both parameters are documented inline; baseline is 3. The description's gloss on min_resolved ('note if fewer than this have resolved') adds a nuance about it acting as a warning threshold rather than a hard gate, but that reading is slightly at odds with the schema's 'before computing metrics' and is not resolved.

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?

States a specific set of verbs and resources: resolve settled snapshots, then compute a reliability curve (predicted vs observed per decile), Brier score, and ECE, with the framing 'tells you whether the market's prices are honest.' That is far more than a restatement of the name. It does not name the sibling polymarket_calibration_snapshot, so the create-vs-score boundary is left implicit.

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?

Provides one genuine usage condition — 'Needs elapsed time for markets to resolve, so it's sparse early on' — which tells the agent when results are worth reading. But there is no explicit when-to-use/when-not guidance and no routing to or from polymarket_calibration_snapshot, which is the obvious complementary tool.

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