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

Annotations declare destructiveHint=true and idempotentHint=true, but the description doesn't explain the destructive nature (dropping the repo connection), confirm idempotency, or clarify openWorld implications. It mentions 'disconnect: true drops the connection' which aligns with destructiveness, but lacks deeper context like permissions, reversibility, or rate limits.

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?

Reasonably concise but includes extraneous workflow details (purchase_scaffold template_files) that confuse the tool's own scope. Front-loads the core action, but the second sentence about purchase_scaffold is tangential.

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?

The tool is simple (1 param, no output schema), so the description covers the basic usage. However, it misses important behavioral aspects like authentication requirements, error conditions, or what happens on repeat calls, and the integration with siblings is only partially explained.

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?

The single parameter 'disconnect' is fully described in the schema (coverage 100%). The description adds minimal extra meaning ('drops the connection'), which is consistent with the schema. Baseline 3 for high schema coverage.

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?

Clearly states it returns a GitHub App install URL for granting repo access and can disconnect. The purpose is understandable, though it's somewhat muddled by mixing in a workflow with purchase_scaffold. Not fully explicit about what the tool itself does versus surrounding steps.

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?

Provides a sequence: open URL, pick repo, approve, then run purchase_scaffold. Suggests signing in with GitHub first. However, it doesn't clearly distinguish when to use this tool versus get_github, and the guidance is tangled with another tool's invocation.

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