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

Annotations already declare destructiveHint and idempotentHint, yet the description adds substantial context beyond them: the exact idempotent result shape (deleted:false, already_deleted:true), the consequence that referencing workflows stop receiving the secret, required permissions and scope, and audit logging with name only.

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?

Front-loaded with the action and target, then idempotency, side effects, auth, and return shape in compact sentences. No filler, and the inline return-shape summary substitutes usefully for the absent output schema.

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, unannotated-output tool this covers everything an agent needs: scope, casing rule, idempotent semantics, side effects on workflows, permission requirements, audit behavior, and return fields despite there being no output schema.

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 100%, so the baseline is 3, but the description adds real meaning the schema lacks — the name normalization rule that cron_secret is read as CRON_SECRET, which affects what an agent must pass.

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 (Delete), resource (one workflow secret), and scope (repository, by name), which is enough to separate it from sibling operations like merjax_set_repo_secret, merjax_list_repo_secrets, and merjax_delete_loop_secret without opening any 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?

Gives clear operational context: idempotent retry is safe, admin access plus 'repo' scope are required. It stops short of explicitly routing the agent to alternatives (e.g. set_repo_secret to update, delete_loop_secret for loop-scoped secrets), so no exclusion guidance is present.

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