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

Annotations mark readOnlyHint=false and destructiveHint=false; the description adds the missing nuance that it reads only, never creates/deletes/overwrites, but may debit credits — which explains the non-read-only annotation rather than contradicting it. It also discloses the auth prerequisite (Ysaere account, not keyless), the credit cost (5), and synchronous return semantics. It doesn't explain why idempotentHint is false, a minor remaining gap.

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 return shape, then routing guidance, then execution semantics, then parameters — a sensible order for an agent scanning it. Some parameter restatement (limit 1–20 default 8, min_similarity default 0.35, file_ids max 50) duplicates the schema and could be trimmed.

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?

Covers the four things an agent needs before calling: what it returns, when to prefer a sibling, auth/cost prerequisites, and sync-vs-poll behavior, which compensates for the absent output schema. What remains thin is failure behavior (empty results, tenant with no files).

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 adds light behavioral framing ('higher drops weaker hits', 'file_ids ... to scope the search') that reinforces rather than merely repeats the schema. The defaults and ranges it cites are already in the schema, so the added meaning is modest.

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 authenticated tenant's Vault') and enumerates the returned fields (chunk_id, file_id, filename, chunk_index, text, score, hit_count), so the agent knows exactly what comes back. It also explicitly contrasts itself with narrated alternatives ('Raw retrieval only — no LLM narrative'), separating it from sourced_brief and quick_brief.

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 an explicit when-to-use ('when you need passages from uploaded files') and names the alternatives with their selection conditions ('sourced_brief ... or quick_brief when you want a written memo'). It also rules out a common misuse pattern by stating it is synchronous and telling the agent not to poll check_report_status.

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