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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds real value beyond that: the hybrid bm25+embeddings retrieval behavior, the default-on report inclusion, and the untrusted-source injection warning about wrapping fetched web bodies in `<untrusted-source>` delimiters. No pagination or rate-limit detail, which keeps it short of a 5.

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-loaded with the purpose and the key behavioral instruction ('send a whole question, not keywords'), and the example object is compact. It is a dense single paragraph packing scope, workflow and a security note; slightly long but almost every sentence carries information.

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?

No output schema exists, and the description compensates by explaining what hits contain (`kind`, `run_id`, `source`) and what to do with them (read_many, cite, run_result). For a 12-parameter search tool, this covers everything an agent needs to select and invoke it 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 every one of the 12 parameters is already documented, including the `tag`/`project` mutual exclusion and the `project` id format. The description reinforces the scoping vocabulary and gives an example object, but adds no semantics the schema lacks — baseline 3 is appropriate.

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 this workspace vault') and immediately narrows scope to evidence notes plus finished reports as `kind: "report"` hits, distinguishing it from list_notes, search_claims and scholar_search. An agent can tell what corpus is searched and what a hit looks like without opening the 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 operating guidance: send a whole question rather than keywords, which facets to scope by, how to obtain project ids (list_projects), and the downstream workflow (read_many the top ids, cite each `source`, pass `run_id` to run_result for report hits). This routes the agent through alternatives rather than leaving inference.

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