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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely non-obvious semantics: one count per value per publication, missing_values for records lacking the facet, and count-descending ordering with pagination. It stops short of stating how filters combine (AND/OR) or how missing_values is returned.

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 dense sentences with no filler, front-loaded with the counting behavior, then accuracy caveats (one count per value, missing_values), then ordering/pagination and the downstream use. Nothing is redundant with the schema.

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 a rich annotation set and a declared output schema, the description does not need to explain return shape, and the counting/pagination semantics plus downstream filter usage cover the essentials. Remaining gaps: no sibling disambiguation against list_years/list_subjects and no clarification of how the 12 filter params compose.

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%, so most parameters are self-documented; the description adds the key insight that the filter parameters scope the counted bibliography. It does not explain semantics for year_from/year_to, keyword scope beyond the schema text, or how `facet` interacts with the returned values. Baseline 3 is appropriate.

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?

Names a specific verb (count) and resource (publications) and enumerates the facet dimensions precisely, which tells an agent exactly what comes back. It does not, however, distinguish itself from sibling list_* tools (list_years, list_subjects, list_categories, list_journals) that plausibly return overlapping value sets.

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?

'Use values in search_publications filters' gives the downstream purpose, and the schema's `type` param echoes the round trip. But there is no when-not guidance, no statement of how this differs from list_subjects/list_years, and no indication of whether the filter parameters must mirror the ones passed to search_publications.

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