count_by_year

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description still adds value by naming the per-row coverage fields (frac_abstract, frac_cc_vor) and explaining what each measures. It does not disclose result size, rate limits, or period boundary handling, which keeps it from a 5.

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 tight sentences, front-loaded with the operation and then the output guardrail. No filler, no restatement of the name, and the parenthetical glosses on frac_abstract/frac_cc_vor earn their space.

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 two-parameter, zero-required, read-only aggregation tool with no output schema, the description supplies enough: what is counted, what `per` accepts, and the shape of each returned row. Missing only how periods are bucketed and whether results are truncated.

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 0% and the schema types are bare strings/anyOf, so the description carries the burden: it enumerates the allowed `per` values (year or decade, beyond the schema's plain string) and characterizes `query` as a title+abstract query. The query syntax (boolean operators, field formatting) is still undefined, preventing a 5.

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 concrete verb+resource ('publication counts over time') and adds the query scope ('title+abstract query') plus the coverage framing. An agent can tell this is an aggregation tool rather than a retrieval tool, though the description never names a sibling like search_works to contrast against.

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 only implied: 'counts over time ... so trends can be judged' hints at trend/series analysis, but there is no explicit when-to-use versus search or search_works, and no exclusions or prerequisites. Sufficient to orient an agent, not to route it confidently among siblings.

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