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

Annotations already flag read-only/idempotent/non-destructive, so the bar is lower, but the description adds meaningful behavioral traits: exact phrase normalization, accent/case insensitivity, bounded context with locators, pagination via nextOffset, and the absence of embeddings/generated summaries. No contradiction with annotations.

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 tight sentences lead with the core action, add the most important return behavior, and include one clarifying caveat about collective publications. Every sentence earns its place; there is no 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?

For a simple read-only search tool, the description is nearly complete: it states what is searched, how matching behaves, and what is returned (context, locators, nextOffset). The absence of an output schema makes the return-value description somewhat high-level, but the combination of annotations and schema constraints covers the remaining operational details.

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?

With 0% schema description coverage, the description carries the burden of explaining parameters. It directly clarifies query ('literal phrases... ignoring case and accents') and publicationId ('public publication's extracted EPUB/PDF text'), and it indirectly covers limit/offset through 'bounded exact context' and 'nextOffset.' However, it doesn't explicitly map limit to result count or offset to pagination position.

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?

The description opens with a specific verb and resource: 'Find literal phrases... in a public publication's extracted EPUB/PDF text.' It also disambiguates from siblings like search_works by scoping to full-text phrase search inside a single publication and by explicitly excluding semantic features ('no embeddings or generated summaries').

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?

The description makes the use case clear: literal, case/accent-insensitive phrase search in a specific publication's extracted text. It implies a contrast with semantic search by saying 'no embeddings or generated summaries,' but it does not explicitly name alternative tools or state when to choose get_publication_text or search_works instead.

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