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

The description says 'Preview', implying a non-mutating dry run, while the annotations declare readOnlyHint=false, i.e. a state-changing operation. That is a direct conflict about whether the call has side effects. The annotations otherwise tell us it is non-idempotent and non-destructive, but the description adds no auth requirements, no duplicate-share behavior, and nothing about what the preview returns.

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?

It is a single short sentence with no filler or repetition, which is structurally clean. But brevity here comes at the cost of substance rather than from efficient compression, so it reads as under-specified rather than concise.

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?

This is a five-parameter access-control mutation with no output schema and no schema descriptions, so the description is the only source of behavioral detail, and it supplies almost none. An agent cannot determine the role semantics, target formats, expiry behavior, or whether a confirming step follows.

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 0% across five parameters, so the description must carry the load, and it does not. It alludes to three target kinds ('user, organization, or public share') while the schema's target oneOf only accepts ACCOUNT and TEAM, so the only parameter hint it gives is partly inaccurate. role, resourceType, resourceId, and expiresAt are never explained.

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 states a verb ('granting') and object ('user, organization, or public share'), so the general intent of granting resource access is visible. However, the leading word 'Preview' muddles whether the call commits a grant or only simulates one, and the title 'Grant resource access' says something different from the description. It also does not distinguish itself from the sibling geobble_resource_share_revoke.

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?

There is no statement of when to call this versus alternatives, no prerequisites (e.g., must the caller have ADMIN on the resource?), and no mention of the complementary geobble_resource_share_revoke for removing access. Usage must be inferred entirely from the name.

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