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

The annotations only declare readOnly=false, idempotent=true and destructive=true; the description adds substantial context beyond that — owner-only authorization, the origin/CSRF and session requirements for the initial grant, how organization API keys are scoped, what revocation blocks, cache headers ('private, no-store'), and the blast radius of the grant across referenced bases.

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 is front-loaded and each sentence carries real information, but the block is dense and drifts into details primarily about the revocation path ('Revocation also blocks search, originals, Markdown, OKF and ZIP downloads') and HTTP caching, which are tangential to invoking this specific tool.

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 two-parameter, no-output-schema grant tool with annotations present, the description covers authorization, scope of access, non-publication semantics, and response caching. The reverse operation and any indication of what the call returns are left implicit, which is a minor rather than blocking gap.

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% and both parameters already carry detailed descriptions (64-char resource ID, organization ID from list_knowledge_teams). The description reinforces the team/collection subject matter but adds no parameter-specific syntax, format, or constraint detail beyond the schema, so the baseline of 3 applies.

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 sentence states a specific verb and resource with scope: 'Give an existing team read access to your collection.' It further distinguishes itself from the adjacent publish flow with 'Sharing does not publish a resource,' so an agent can separate it from publish_collection and share_base_team without opening either 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?

It establishes the trigger condition (grant read access to an existing team) and carves out the nearest confusing alternative by stating that sharing is not publishing, plus who may invoke it ('Only the resource owner changes sharing'). It never explicitly names unshare_collection_team or a when-not-to-use case, so it stops short of full routing guidance.

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