Check references

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

Beyond the readOnly/idempotent/openWorld annotations, it discloses a real operational constraint (ADS allows only 100 resolver requests a day), the meaning of result statuses (CHECK, NOT FOUND) and how to present partial mismatches to the user. That is behavior an agent could not infer from annotations or 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?

Purpose is front-loaded in the first clause, followed by usage, batching constraint, and status semantics in descending priority. Every sentence carries actionable content; the note about showing the user both the written and resolved reference is substantive, not filler.

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 explaining return values and does so: bibcode lookup plus a match verdict across first author, year, volume and page, with the CHECK and NOT FOUND states defined. For a single-parameter read tool with rich annotations, nothing an agent needs to call it correctly 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?

Schema coverage is 100% and the schema already documents the array, its maxItems of 100, and the accepted free-text style. The description still adds meaning beyond it by prescribing one reference per item and the strategy of batching the entire bibliography into a single call for rate-limit reasons.

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 ('Check a list of references ... against ADS') plus the exact output ('finds each paper's bibcode and says whether the reference matches'). It also names the sibling tools it feeds into (export_bibtex) and the fallback (search_papers), so an agent can place it precisely in the toolset.

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 explicit use cases ('verify a bibliography or to get bibcodes for export_bibtex'), an explicit alternative for the failure case ('For NOT FOUND, try search_papers with the first author and a few title words'), and batching guidance ('send a whole bibliography in one call'). Both when-to-use and what-to-do-instead are covered.

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