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

The description goes well beyond annotations by disclosing the delegation model: 'use' runs tools under the delegator's authority, not the grantee's, including through synthetic entry steps. It also reveals that re-sharing is an update rather than a new grant, that responses repeat a delegation summary, and that 'user' shares return grantee identity details. This is rich behavioral context beyond readOnly/destructive/idempotent hints.

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?

The description is dense but not bloated; every sentence carries operational or behavioral guidance. It front-loads the primary purpose and access levels, then covers conditional parameters, idempotent behavior, delegation semantics, and response shape. The main weakness is that these important topics run together in one long paragraph rather than being separated for quick scanning, but no sentence is wasted.

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 complex tool with no output schema, the description fully compensates: it explains the conditional grantee_id rule, the three levels, delegation consequences, update-on-reshare behavior, the response structure, and how to interpret the returned delegation summary. It tells an agent everything needed to invoke the tool correctly and understand what it returns. No critical information appears 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 crucial meaning the schema cannot express: grantee_id is conditionally required, must be omitted for 'org', and is required for 'user' and 'team' despite not appearing in the required array. It also explains the level enum values and the output's grantee object. This is meaningful added value over the schema, though the schema already documents most parameter names and types.

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 description clearly states the verb and resource: 'Grant a person, a team, or the whole organization access to a toolbox.' It defines the three access levels with concrete meanings ('view', 'use', 'edit'), and this distinguishes it from nearby sharing tools like connection.share and template.share by explicitly scoping to toolbox access. The purpose is immediately identifiable and unambiguous.

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?

The description gives clear context on when this tool applies (granting/re-granting toolbox access) and explicitly names toolbox.unshare as the alternative for removing access. It also explains that re-sharing to the same grantee updates the level rather than creating a duplicate grant. It does not explicitly enumerate when NOT to use this tool versus all sibling alternatives, so it falls just short of a 5.

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