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

Annotations cover idempotency and safety hints, and the description adds substantial behavior beyond them: sharing is read-only, secrets are hidden, environments are never shown, export is impossible, and the returned link is immutable. That is exactly the kind of context annotations cannot supply.

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 action and inclusions, then defaults, then the return value — a logical order with no filler sentences. It is dense, but every clause conveys a distinct constraint.

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 still states the return value (the collection link) and its immutability, and covers the mutation's side effects and sharing scope. Only minor details, such as what an invite email contains or failure modes, are left implicit.

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 67%, and the description compensates by explaining when to supply `link_access` and `invite` (only for out-of-team sharing), reinforcing the schema's 'omit to keep current setting' note. `collection_id` carries no description anywhere, but it is self-evident from the name.

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 ('Share a whole collection') and immediately scopes what is included (every endpoint, examples, latest run). It is clearly distinguishable from the sibling share_api_endpoint, which shares one endpoint rather than the whole collection.

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 defaults and exclusions: with no other arguments it stays restricted to the workspace, and `link_access`/`invite` should be set 'only when the user asks to share it outside the team'. It also cross-references get_api_collection as the way to retrieve the link.

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