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

Annotations already declare readOnly/idempotent/no-open-world, but the description adds non-obvious operational context the annotations cannot: a local model run, a ~350 MB first-use download cost, and the fact that similarity_score is not comparable across queries. These are exactly the behaviors an agent needs before invoking.

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?

Four short sentences, each carrying distinct information: capability, coverage limit + alternative, runtime/download cost, score interpretation caveat. The core capability and the sibling fork are front-loaded with zero 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 7-parameter read-only search with no output schema, the description covers the things the structured data cannot: corpus coverage gaps, first-use latency/download, and how to interpret similarity_score. An agent can decide between this and search_references and set expectations correctly.

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 description coverage is 100%, so the schema already documents all seven filters, setting the baseline at 3. The description adds genuine value by clarifying what the free-text query is matched against (title + abstract) and that query language is unrestricted, which shapes how the agent formulates the query.

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 ("Semantic search over academic references"), plus the indexed fields (title + abstract) and language scope. It is immediately distinguishable from search_references, which the description names as the lexical counterpart.

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 the agent: this tool covers only the ~50% of references with abstracts, and search_references must be used for the rest. That is a concrete when/when-not rule naming the alternative, not implied usage.

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