Create Grant

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the crucial reason: an existing grant is replaced, and that replacement can lower the recipient's access. That is real value beyond the structured fields and directly explains the destructive flag. It stops short of covering required permissions or whether the recipient is notified.

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 short sentences with zero filler: the action and its scope come first, and the destructive edge case follows as a warning. Every clause carries information an agent needs.

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 an output schema present, the description needn't describe return values, and annotations cover mutability and openness; the description closes the remaining behavioral gap by explaining the role-replacement effect. It is slightly thin on prerequisites and on how it differs from 'share_deck', which keeps it from a 5.

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 schema already documents 'subject' (user id or email creating an EMAIL grant) and 'role' (access level enum). The description reinforces that subject accepts an ID or email and adds that only a single subject is accepted, but contributes nothing for the undocumented 'deck_id'. Baseline 3 is appropriate given the schema does most of the work.

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 gives a concrete verb and resource ('Share a deck'), scoped to exactly one recipient ('one person, by user ID or email address') at a specified role, so an agent knows precisely what the call does. However, it never distinguishes itself from the sibling tool 'share_deck', so the agent must guess which of the two performs which sharing operation.

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?

Usage is only implied: the phrase 'one person' suggests this is the single-recipient path versus some broader sharing path, but no alternative is named and no preconditions (ownership/admin rights on the deck) are stated. The caveat about replacing an existing role is genuinely useful context, but it describes an effect rather than when to choose this tool.

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