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

Annotations already declare read-only, non-destructive, closed-world. The description adds real value beyond them: the default filter-out of sponsored content, the newest-first ordering, and the fact that results are summaries with provenance rather than full records. No return shape or pagination behavior is described, but with readOnlyHint already carrying safety, the remaining gap is minor.

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?

Three sentences, each doing distinct work: what it searches and ordering, how to filter and the sponsored exception, and what it returns plus the sibling alternative. No waste and the scope is front-loaded.

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 filter-only read tool with 5 optional params, 80% schema coverage, and no output schema, the description covers scope, default behavior, result granularity, and the escalation path to get_story. Missing only minor operational details like max limit behavior (which the schema's maximum=20 already supplies).

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 80%, so the baseline is 3. The description adds meaning the schema doesn't: the include_sponsored flag's default-off behavior and the consequence of the exclusion, plus the date/beat/text filtering intent. The sponsored semantics are the most valuable addition; other parameters are covered by the schema descriptions.

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 verb and resource ('Search published Agentry stories'), plus ordering ('newest first'). It explicitly distinguishes itself from get_story by describing summaries/provenance versus full text, so an agent can tell the two apart without opening a schema.

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?

Clear usage context: filter by text/beat/date, and the description routes the agent to get_story when full text is needed. It also explains the default exclusion of sponsored stories. It stops short of naming list_beats as the source for beat slugs, though the schema does that.

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