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

Annotations already declare readOnlyHint=true, so the safety profile is covered, but the description adds real behavioral context: what the plan reports (eligible vs. blocked usages with reasons) and that a repository sync may be a prerequisite. It does not describe the plan's return format, which slightly limits it.

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: the first front-loads the action and enumerates the plan's scope, the second establishes the planning-only constraint and the applying sibling. 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?

With no output schema, the description compensates by explaining what the plan determines (eligibility, blocking reasons, sync requirement), which is effectively the shape of the result. Combined with the read-only annotation and complete schema, an agent has everything needed to invoke it correctly.

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 100%, so credential_id, target_credential_id, and usage_resource_ids are fully documented in the schema. The description adds no syntax or usage detail beyond that, which is the expected baseline when the schema carries the weight.

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 states a specific verb (build the plan) and resource (swapping a deprecated GitHub OAuth credential to a GitHub App credential), and enumerates exactly what the plan resolves: eligibility of GitOps usages, blocked usages with reasons, and sync requirements. It is clearly distinguishable from sibling tools like get_github_credential_usages and replace_github_credential.

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?

It explicitly scopes this as planning only and routes the agent to replace_github_credential for the actual application, establishing the correct order of operations. It lacks an explicit statement of when to prefer this over get_github_credential_usages, but the context is unambiguous.

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