start_work

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

Annotations only supply destructiveHint=false, so the description carries most of the burden. It does disclose the actual mutation — status set to In Progress and assignment to the caller — which is genuinely useful beyond the annotations, but it says nothing about prerequisites, idempotency (what happens if the issue is already In Progress), permission requirements, or what "context" is returned.

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?

Four words plus a colon — nothing is padded and the effects are front-loaded. The telegraphic fragment style trades clarity for brevity, but no sentence is wasted.

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 5-parameter workflow mutation with no output schema and only 40% schema coverage, the definition is too thin. "Return context" is undefined, and the caller cannot predict the failure modes or the returned payload before invoking it.

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 40%, below the threshold where the schema alone suffices. The description only echoes values already encoded as schema defaults (statusName="In Progress", assignToMe=true) and leaves the confusing overlap between claimAs and assignToMe, plus the undocumented workspace parameter, entirely unexplained.

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?

"Pick up issue: In Progress, assign me, return context" names a concrete action and its three effects (status transition, self-assignment, context payload), so an agent knows what happens without opening the schema. It does not, however, differentiate itself from the sibling claim_issue, which plausibly does something very similar.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no alternative is named. The presence of sibling tools like claim_issue and finish_work makes the omission costly: an agent cannot tell whether start_work supersedes or complements claim_issue.

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