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

Annotations already declare idempotent=true and destructiveHint=false, but the description adds real substance beyond them: the follow record is 'marked stopped and kept' rather than deleted, and 'open mirror positions stay yours to manage' clarifies downstream side effects. It also states the return value ('the stopped record, or says there was none'), covering the no-op case.

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?

A single tight sentence with the action front-loaded and the side effects and return value following in order of importance. Minor ambiguity in 'at once' (immediately vs. simultaneously), but no wasted text.

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 mutation tool with no output schema, the description supplies what the structured fields can't: the soft-delete semantics, the untouched mirror positions, and the return value including the none case. Annotations cover the safety profile, so nothing an agent needs is missing.

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?

Only one parameter ('model'), and schema description coverage is 100%, so the schema already documents it as 'the model's attribution'. The description adds nothing about the parameter format or identifiers beyond the schema. Baseline 3 applies when the schema carries the load.

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+resource ('Stop following a model') and immediately scopes it with the eligibility clause 'any tier may stop'. The inverse relationship to the sibling 'follow'/'follows' is obvious, though no sibling is named explicitly to rule out confusion with 'follow_quote' or 'replay_open'.

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?

'Any tier may stop' is a genuine eligibility/prerequisite disclosure that tells the agent who can invoke it, and the use case (stop an active follow) is clear from the verb. It stops short of naming an alternative tool or a when-not condition, so it doesn't reach the top band.

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