Start session

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

Annotations only confirm it is a non-read-only, non-destructive write; the description adds substantial unique behavior: the ok|stop|plan_first verdict, the guard that no session is created on 'stop', the override escape hatch, and that multiple concurrent sessions share attention by weight. This is rich context beyond the structured fields.

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-loads the action and the timer nuance, then layers in the verdict, the stop guard, and concurrency. Dense but every clause carries information; no wasted 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?

For a 12-param, mutation tool with no output schema, the description covers the highest-value unknowns: the return verdict values, the stop/override workflow, and concurrency semantics. Remaining params are handled by the schema, so it is nearly complete.

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 75%, so the schema already documents area, weight, direction, minutes, and override. The description mostly reinforces these (share attention by weight, override=true) rather than adding new parameter meaning, matching the baseline 3.

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 ('Start a session of work and, if none is running, the timer') with an unusual dual effect. It doesn't explicitly differentiate from close siblings like add_session or split_attention, which could be confused with starting a session.

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 strong conditional guidance for the 'stop' verdict (relay the message, ask the user, retry with override=true), but says nothing about when to choose this over add_session or split_attention. Usage is implied rather than contrasted with alternatives.

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