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

Goes well beyond the annotations: it discloses that starting a job pauses the technician's other started job, that account-level 'job started' notifications (email/SMS/webhook) may fire to managers, technicians or the customer, and names the underlying POST /job/start endpoint. These are non-obvious side effects an agent must anticipate before invoking, and they align with (rather than merely repeat) destructiveHint/readOnlyHint.

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 dense paragraph with zero filler: the mutation flag and outcome are front-loaded, followed by side effects, then the identifier rule and endpoint. Every clause carries information an agent needs.

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 mutation tool with no output schema, the description covers outcome, side effects and identifier selection, which is most of what is needed. It stops short of stating what happens on an already-started job (annotations say idempotentHint=false, but the description stays silent) or what response/record is returned.

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 baseline is 3, but the description adds a constraint the schema does not encode: the three identifiers are mutually exclusive and exactly one must be supplied. That is real added value for a schema with zero required parameters and no oneOf/anyOf construct.

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 (mark a job as started) and clarifies the concrete effect (status 'started', actual start timestamp now), which is more than the name and title convey. The 'WRITE:' prefix plus the start-state semantics cleanly separate it from siblings such as synchroteam_complete_job, synchroteam_create_job and synchroteam_schedule_job.

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?

It gives a concrete selection rule for identifiers ('exactly one of id, my_id or num'), which is genuinely useful. However, it never states when to choose this tool over synchroteam_complete_job or synchroteam_schedule_job, nor any precondition (e.g. only for jobs in a pending/assigned state). Usage is only implied from the verb.

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