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

Annotations already cover the safety profile (readOnlyHint, idempotentHint), so the description only needs to add context. It does so by framing the output as the 'full record' versus get_grant's 'public facts', implying depth and possibly privileged data. It does not mention auth requirements or whether the record can be partially populated.

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?

Two tight sentences with zero filler, and the primary purpose is front-loaded before the sibling routing instruction.

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 single-parameter read with no output schema, the description plus annotations give enough to call it correctly and interpret the result as a full record. Missing only peripheral detail such as error behavior for a non-showcase UUID.

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?

One parameter with 0% schema description coverage, but format=uuid in the schema already communicates the key type. The description's 'by UUID' is real but minimal semantics; it adds nothing about whether the UUID is the grant ID, a showcase ID, or where to obtain it.

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 (Read), resource (one showcase grant's full record), and the lookup key (UUID). It explicitly distinguishes itself from the sibling get_grant rather than leaving the agent to infer the difference.

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 both the when ('one showcase grant') and the when-not plus alternative ('For any other grant use get_grant, which returns its public facts'). Routing between this tool and its closest sibling is spelled out.

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