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

Annotations already declare readOnlyHint and destructiveHint=false, but the description adds substantial behavior: results are ranked and not guaranteed complete, archived documents are hidden by default, default filters hide unverified-by-others/archived/tainted docs and report them in an 'excluded' count, and each hit carries is_own, created_by, trust, matched_chunks, and tenant_alias when shared. Gaps: it never explains what 'mode' controls (hybrid vs. other values) or include_tainted, and 'returns summaries only' is only sketched.

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?

Paragraphs are front-loaded and organized by concern (scope, flags, filters), and the most decision-relevant caveat comes first. It is dense but each sentence carries information; the final fragment ('query adds hybrid ranking; returns summaries only') is tacked on and reads less cleanly than the rest.

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 not be spelled out, and the description still usefully names the hit fields and the excluded counter. For a 10-parameter tool the coverage is strong; the missing pieces are the semantics of 'mode' and 'include_tainted', which matter given mode defaults to 'hybrid' and drives the ranking behavior described.

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 0%, so the description must carry the burden and mostly does: limit default (10) and cap (50), include_own_unverified vs include_unverified defaults and intent, include_archived, include_shared, and a full operator grammar for filters with a worked example. However, 'mode' (the default-driver parameter) and 'include_tainted' are never explained, leaving two of ten parameters opaque.

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 opening line names the resource (documents) and the operation (hybrid structured + semantic ranked discovery), and immediately qualifies the scope with 'semantic search, NOT exhaustive'. It explicitly contrasts itself with list_documents (enumeration) and workspace_sync (L0 map/incremental changes), so an agent can distinguish it from its nearest siblings 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?

States when to use it (ranked best-match retrieval) and when not to, naming the two concrete alternatives and the conditions that select them: list_documents for full enumeration with cursor pagination, workspace_sync for the L0 map and incremental changes. It also gives filter/flag conditions that change behavior (include_archived, include_shared).

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