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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: the return shape, the 25-rows-per-page pagination behavior, and the grade/verdict semantics, which the agent needs to interpret results.

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?

Two dense but well-ordered sentences: returns first, then filters, then pagination. Every clause carries information, though the verdict thresholds duplicate what the schema already states, creating slight redundancy.

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?

With no output schema, the description carries the burden of describing returns, and it does so thoroughly (fields plus grading arithmetic). For an 11-param, all-optional filter tool with high schema coverage, this is complete enough; only explicit sibling routing is missing.

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?

With 91% schema description coverage, the schema already documents nearly every parameter. The description restates the verdict thresholds (which already appear in the verdict schema description) and clarifies that claimedAfter/claimedBefore filter on publication date, adding only marginal value over 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?

States a specific resource (individual NFL predictions) and enumerates what each take contains — pundit, date, excerpt, grade, grading arithmetic — so the agent knows exactly what is being listed. It does not explicitly contrast itself with siblings like pundit_record or leaderboard, which would be needed for a 5.

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?

Usage is implied through the filter list and the pagination note ('pass page for more'), which tells the agent how to page. However there is no explicit when-to-use or when-to-prefer-an-alternative guidance (e.g. pundit_record for a single pundit's summary), leaving the routing decision to inference.

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