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

Annotations already establish read-only and idempotent behavior. The description goes further, disclosing permission boundaries (no approval capability, no exposure of the stored change) and the retry-after-approval semantics, though it says nothing about response shape or expiry semantics beyond existence.

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 tight sentences, front-loaded with the core action, then constraints, then next steps. No filler.

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?

Output schema exists, so return values needn't be explained, and the safety profile is covered by annotations plus the permission disclaimer. The only real gap is parameter context, which leaves the definition nearly complete for a simple read tool.

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 0% and the single required parameter approvalId is never mentioned or explained in the description. The UUID format/pattern in the schema helps, but an agent gets no guidance on where the approval ID comes from or what it identifies.

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?

Specific verb and resource: check status and expiry of an app approval for this connection. Clearly distinguished from sibling approval tools (get_approval_request, list_approval_requests) by scope and by stating it cannot approve.

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 actionable workflow guidance: cannot approve or reveal the stored change, ask an Admin/Owner to review in the app, and retry the exact change only after approval. Doesn't explicitly contrast with siblings like get_approval_request, so not a 5.

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