Approve and execute

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

Beyond the annotations (destructive, open-world, non-readonly), the description adds real operational context: the write is gated on an approval token, the confirm flag is mandatory, and the call is single-use. The single-use note also refines retry safety ('repeating it returns the stored outcome without re-executing'), which is actually safer guidance than the conservative idempotentHint=false annotation, so this is a refinement rather than a contradiction. Not disclosed: whether approvals expire, what the stored outcome contains, or what failure modes (expired/stale approval_id) look like.

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?

Three short sentences, front-loaded with what it does and its unique position among siblings, then preconditions, then retry semantics. No filler and nothing that restates the title.

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 destructive, token-gated mutation with no output schema, the description covers the essential call requirements (approval source, mandatory confirm, single-use outcome). It does not describe the returned outcome shape or error conditions for invalid/expired approvals, which leaves a modest blind spot for an agent handling failures.

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%, so the description must carry parameter meaning, and it only covers half: it confirms the semantics of 'confirm' (must be true) and implies where approval_id comes from. It says nothing about approval_id format, scope, or lifetime, which matters for a destructive, non-repeatable operation. Partial compensation for a documented-coverage 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?

States a specific verb and resource ('Execute a pending approval created by an instagram_preflight_* tool') and immediately scopes it against the whole sibling family: this is the only tool that mutates Instagram, everything preflight_* merely stages. An agent can distinguish it from instagram_get_operation or any preflight tool without opening a schema.

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?

Preconditions are explicit: an approval_id must already exist from an instagram_preflight_* call, and confirm must be true. 'This is the only tool that changes Instagram' effectively routes the agent here for any write. The only gap is the negative case – it never says what to do if no approval exists (i.e., go run the matching preflight first), which is left to inference.

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