Record a safe stop

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

Annotations already declare write/non-destructive/non-idempotent/openWorld=false, so the safety profile is covered; the description still adds real value by disclosing append semantics ('preserving earlier stops without moving/closing focus') and by reporting uncommitted, unpushed and unclaimed changes since no output schema exists. It does not say whether repeated calls create duplicate stops or how focus interacts with the save, which matters given idempotentHint=false.

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?

Three short sentences, front-loaded with the action and scope, then usage, then return content, then the read/write boundary. No filler; the telegraphic density is deliberate and each clause carries information.

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 two optional params, no output schema, and a non-destructive write, the description covers what an agent needs: when to call it, that it appends rather than replaces, and what the call reports back. The only residual gap is non-idempotency behavior on repeat calls, which is left to the annotation hint alone.

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 both parameters are documented in-schema, so the baseline of 3 applies. The description restates 'label and next step' but adds no format, length, or defaulting nuance (e.g., what happens when label is omitted) beyond what the schema already says.

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: recording a safe point with a label and a next step, and adds differentiating scope ('preserving earlier stops without moving/closing focus'). The closing 'it does not read the last stop' separates it from read-side siblings. It stops short of naming which sibling (vivac_park, vivac_done, vivac_pop) is the near-miss alternative for the same workflow.

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?

'Use before stopping or handing off' gives an explicit trigger condition, and 'This writes; it does not read the last stop' supplies an implicit when-not. There is no explicit exclusion naming the sibling to use when the agent actually wants to read or retrieve state, so the routing guidance is clear but not complete.

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