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

Annotations already declare idempotent=true, destructive=true and readOnly=false, and the description usefully scopes the blast radius: only the caller is removed, while the opener and commenters still receive emails. It also adds non-obvious operational facts (writes are marked 'via AI agent', files cannot be attached here) though it does not explain reversibility or error behavior on an unknown case_id.

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?

The core action is front-loaded, but the text restates the same fact twice in near-identical words ('Removes the caller from the followers. The opener and people who wrote in the case still get its emails' then 'Stop following. The opener and people who wrote in the case keep getting its emails'). A large block of general support-case boilerplate is disproportionate for a one-parameter idempotent toggle.

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 one-parameter, non-destructive-to-others idempotent toggle with no output schema, the description covers effect, scope of who is affected, notification behavior, attachment limitations, and attribution of the write. Little an agent needs in order to call it correctly is missing, aside from guidance on switching to follow_support_case.

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%, and the single case_id parameter is fully specified in the schema with its pattern and format. The description adds no syntax, format, or meaning beyond what the schema already provides, so the baseline 3 applies.

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 (stop following a case) and immediately clarifies the effect: removes the caller from the followers. It also positions the tool within the support-case domain versus issues (create_issue, search_issues), so an agent can separate it from that cluster of siblings 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?

The description gives strong domain-level routing (support cases vs issues, never for the user's own project work) but never states when to invoke unfollow specifically versus follow_support_case, list_watchers, or unwatch_issue. The practical trigger — the user no longer wants case email — is only implied by 'Stop following'.

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