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

Annotations already declare read-only/idempotent/non-destructive, but the description adds real behavioral context: filters are AND-combined, results are newest-first, keyword penetrates extracted PDF text (surfacing matched_in='fulltext' plus a snippet for text-only hits), exports omit abstracts/full text, and amira_url should be the citation link. This goes well beyond the annotation surface.

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?

Information-dense with no filler sentences, and the core purpose plus scope is front-loaded. It is slightly packed with parallel clauses (export, pagination, citation) that could be separated, but every sentence earns its place.

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 12-parameter, no-required-argument search tool with no output schema, the description supplies the missing return semantics: matched_in, snippet, has_more, next_offset, and citation link guidance. Nothing an agent needs to call or iterate it correctly is absent.

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 75%, so most parameters are self-documented, yet the description still adds meaning: keyword's reach into full text, citation_format's effect on output completeness, and the AND semantics across filters. It stops short of clarifying ambiguous params like year_from/year_to bounds or has_fulltext interaction.

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 ('Search the ERef/EPub cluster bibliography') and immediately distinguishes itself from siblings by naming list_publication_facets for discovery and get_publication for detail. An agent can tell what this tool does without opening any schema.

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?

Explicitly routes to alternatives with conditions: use list_publication_facets for facet values, get_publication for detail, and set citation_format when exporting. Also gives the iteration protocol (follow next_offset until has_more=false), so when and how to use it are both covered.

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