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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial behavior beyond them: the single-vector padding failure mode with measured rank evidence, ranking by similarity rather than canonical importance, and the fact that `language` does not affect matching or ranking. No contradiction with readOnlyHint/idempotentHint.

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?

Front-loads the purpose, then the critical query-padding warning, then alternatives and hints. It is long and somewhat repetitive in emphasizing the no-padding rule, but the measured rank example and the keyword-vs-semantic distinction earn their space for a nuanced retrieval tool.

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?

An output schema exists, so return values need no explanation; the description covers everything else an agent needs — query form, limit tuning, language behavior, ranking caveats, and sibling routing. Nothing material is missing for correct invocation.

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 100% (baseline 3), but the description goes well beyond it: it warns that default `limit=5` is too small for topic surveys and recommends 15–20 (max 20), explains that `language` only controls output and not matching, and gives concrete query construction rules. This is real added meaning over the schema's terse one-liners.

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+resource ('hybrid search — combines keyword + semantic search via RRF') and immediately distinguishes itself from siblings by naming search_by_keyword and search_semantic in the usage guidance. An agent can tell it apart from the other two search tools without opening a 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 states when to use it ('discourses about X / concept queries'), when not to use it (concrete things like animals/objects/places → search_by_keyword over language="english"), and what to do with candidate terms (separate search_by_keyword call, merge lists). Includes an explicit exclusion: don't fold keyword terms into the query string.

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