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

No annotations are provided, so the description carries the full burden. It discloses key behavioral traits beyond the schema: the run starts already Working, the issue status is unchanged, the issue becomes locked so edit_issue and delete_issue fail while status changes and comments still work, the tool fails if an open run exists, and it returns the run. These are exactly the side effects and failure modes an agent needs before invoking a mutating operation.

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?

The description is appropriately sized and front-loaded: it states the core action first, then differentiates from create_agent_run, then lists failure and locking behavior. Every sentence adds useful information, though the dense multi-clause sentences could be marginally tightened without losing meaning.

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 complex mutation tool with no annotations and no output schema, the description is complete enough to invoke correctly. It covers lifecycle, prerequisites, permission requirements, failure conditions, locking side effects, and return value, leaving no major gap an agent would need before calling 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 100%, and the single issueKey parameter is fully documented in the schema. The description adds contextual constraints around who can start a run and which issue states are allowed, but it does not add syntax or format details beyond the schema. A baseline 3 is appropriate because the schema already handles parameter semantics.

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?

The description uses a specific verb+resource ('Starts an agent run') and immediately defines the exact state and scenario: a run already Working for an agent working with a person outside a hand-off. It explicitly distinguishes this from create_agent_run and names the lifecycle siblings finish_agent_run and cancel_agent_run, so an agent can differentiate it from siblings without opening schemas.

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 states exactly when to use this tool versus create_agent_run ('Unlike create_agent_run, the issue may be in any status and its epic needs no particular statuses'), when not to use it ('Fails when the issue already has an open run'), and what alternatives exist for ending the run (finish_agent_run or cancel_agent_run). It also gives a permission prerequisite: only the issue's assignee can start one, with canEdit from get_issue/list_issues.

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