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

The annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is fully covered without prose. The description adds one genuine behavioral fact not in structured data: only *published* re-runs are indexed, and an empty query enumerates everything. It says nothing about the shape of a result entry or how to page past the limit, which matters given there is no output schema.

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 sentences, no filler, with the primary action and indexed fields front-loaded and the empty-query edge case placed second. Every clause carries information the agent cannot get elsewhere.

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 four-parameter, zero-required search tool with full annotations, the definition covers scope, fields searched, filters and the no-query case adequately. The remaining gap is the return shape and whether results are paginated beyond the 50-item limit, which the description does not address and there is no output schema to compensate.

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?

Adds real meaning beyond the schema by specifying that the query matches words across title, authors, venue and field, where the schema only says 'words to match'. It also frames outcome and field as optional filters, consistent with the 75% schema coverage. The limit parameter is left entirely to 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 verb and resource ('Search published re-runs') plus the indexed fields (title, authors, venue, field) and optional filters, so the agent can tell this is a discovery/search tool rather than a fetch tool. It does not explicitly contrast itself with siblings like get_report or check_paper, so identification rests on the verb alone.

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?

Gives clear context on when this applies: broad keyword search with optional outcome/field narrowing, and explicitly states the degenerate case ('With no query, lists the whole ledger'), which is exactly the kind of guidance an agent needs to avoid guessing. No exclusions or named alternatives are provided, so it stops short of full routing guidance.

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