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

Beyond the annotations (non-readonly, idempotent, not destructive), the description adds real behavioral context: link visibility requires sign-in to Crow's Nest, only public access skips sign-in, membership is changed by email addresses, and aiDiscoverable is off by default and only valid for public tools. It does not state what happens to existing collaborators when visibility is downgraded, nor what the response looks like, but the added context is substantial.

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 trigger phrase, then the visibility options, then the modifier flag semantics; nearly every clause carries information. The nested parenthetical about sign-in is dense and slightly harder to parse, but nothing is redundant.

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 5-parameter mutation tool with no output schema and no annotations covering permissions, the description covers the meaningful semantics of visibility and aiDiscoverable well. It leaves out the meaning of toolId, whether the caller must be an owner/admin, and what the tool returns or what happens when the last collaborator is removed.

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 only 20%, so the description has to compensate, and it does: it decodes the visibility enum semantics (private, specific people, link with sign-in, everyone at the company, public), explains that add/remove take email addresses, and clarifies the default and constraint on aiDiscoverable. The required toolId parameter is not explained at all, which is the remaining gap.

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?

Names a specific verb and resource (change who can open a tool) and enumerates the visibility levels that the operation sets, which makes the purpose concrete. It does not name or differentiate against siblings (publish, delete_tool, find_tools), so an agent must infer that this is the permission-editing tool rather than publication or discovery.

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?

"Use when the user wants to change who can open a tool" is an explicit trigger condition. However, there is no when-not guidance, no mention of prerequisites (ownership/admin rights), and no routing to alternatives such as publish or org_member_update, leaving the agent to guess on ambiguous sharing-versus-publishing requests.

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