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

Annotations already cover the safety profile (read-only, idempotent), and the description adds substantial behavior beyond them: hybrid→keyword fallback trigger conditions, `meta.mode` signalling, the distinction between indexing attached source documents rather than the records, `rerank_score` sign meaning, and `empty_result.near_misses` on over-filtering. This is exactly the kind of context annotations cannot express.

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 two-mode split in bold labels and each sentence carries operational information. It is long and a few clauses (rerank score sign, near_misses) restate schema descriptions, but nothing is padding for its own sake.

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 9-parameter hybrid search tool with an output schema, the description covers modes, fallback semantics, coverage caveats, downstream id handoff, and scoping defaults — the remaining gaps (return format details) are handled by the output schema.

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%, so the baseline is 3; the description nonetheless adds discriminating meaning — that `min_rerank` is the meaningful filter while `min_similarity` is coarse, that `dapper_content_id` is the record id to pass downstream, and that `country_code` omission differs from 'all'. It slightly duplicates the schema's own `min_rerank` text, keeping it from a 5.

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+scope: cross-domain search over the full document corpus, with two explicitly named modes (`q` search vs `document_id` metadata fetch). It also names the sibling tools it overlaps with (domain list_* tools, get_document_text), so an agent can distinguish it 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?

Gives explicit when-to-use rules: use `q` unless `document_id` is given; prefer a domain tool's own `q` when the domain is already known; use `domain=` to scope; omit `country_code` only when you accept the default country. It also flags that empty results are inconclusive due to uneven coverage — a real usage caveat, not boilerplate.

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