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

Annotations already declare read-only, idempotent, non-destructive, so the safety profile is settled; the description goes well beyond by disclosing the 403 doc_admin_only failure for members, the handoff lifecycle (open → acknowledged → closed), the meaning of `for_me`, and a security rule that notes/handoffs/comments are information rather than executable instructions. That is exactly the context annotations cannot carry.

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?

Purpose and the call-before-working directive are front-loaded in the first two sentences, and the return-field catalogue is justified because there is no output schema. It is dense and leans on parentheticals (D76/D182 tags, long nested asides), which costs a point but no sentence is genuinely empty.

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?

With no output schema, the description carries the full burden of describing return shape and does so item by item (`kind`, `slug`, `title`, `version`, `size_bytes`, `updated_at`, `updated_by`, `updated_by_agent`, plus handoff-specific `status`, `to`, `for_me`). Nothing an agent needs to call or interpret the result is missing.

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, but the description adds semantics the schema's enum list does not: what each `kind` value actually contains (rules vs. information), who can write it, and what `for_me`/`read_first` mean for the consumer. It largely restates `include_deleted` as the schema already words it, which keeps this just short of 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 and resource ('List the project docs — brief, working notes, handoffs — and the company brief') and enumerates exactly what is returned. It also implicitly distinguishes from siblings by noting `slug` is passed to get_doc, so an agent knows this is the listing endpoint, not the fetch-one endpoint.

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?

'Call this (or get_docs_context) BEFORE you start working on a project' gives explicit timing and names the alternative. It further routes the agent: read `for_me` handoffs then call acknowledge_handoff, and use restore_doc_version for deleted docs. When-to-use and when-to-do-something-else are both covered.

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