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

Goes well beyond the readOnly/idempotent/openWorld annotations: it discloses no login, no storage of inputs or reports, that registry text is untrusted data, and that output is field differences plus uncertainty rather than a truth verdict. These are exactly the behavioral facts an agent cannot get from structured fields.

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 with the core action and scope, then safety and interpretation caveats in short declarative sentences with no filler. The telegraphic style is dense but every clause carries a distinct constraint; it reads slightly like a list rather than prose.

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 return-value burden and does so at a high level: field differences, uncertainty, per-status reading. Exact response fields are not enumerated, but the interpretive guidance (existence does not prove claim support) is the more valuable information for correct use.

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 67% and the schema already documents text, search_titles, and item fields, so baseline would be 3. The description adds real meaning on top: the 1–10 cap, the public-only restriction, and the fact that search_titles explicitly authorizes sending titles to Crossref and yields unverified candidates.

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 with explicit scope: 'Check 1–10 public DOI/arXiv references against Crossref/DataCite'. The scope (1–10 items, public references, two named registries) is precise enough that an agent knows exactly what the tool does, and none of the sibling tools overlap with this function.

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 conditions: only public references, title-only entries go to Crossref only when search_titles:true, and it warns to read each status rather than inferring support. There is no explicit 'use this instead of X' routing, but no sibling tool is a plausible alternative, so the gap is minor.

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