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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the safety profile is covered. The description adds genuine value beyond that: it explains the run lifecycle, that finish_run produces a Markdown report for a PR, and that the run is visible in the app. It does not, however, warn that repeat calls create separate runs or note any auth requirements.

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 purpose is front-loaded in the opening clause, which is good, but the second sentence is a long, comma-heavy enumeration ('the code or the link's site (never its query), checks, and emails that never came') that is hard to parse and spends words on sibling tools rather than this one.

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 no output schema, the description usefully conveys the surrounding workflow and what finish_run yields. It does not explicitly state what start_run itself returns (a run_id), though that is strongly implied by the instruction to pass run_id onward, leaving a small gap for a tool whose output the agent must capture.

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% with all six parameters documented in the schema (name, agent, branch, commit, repository, pull_request), so the baseline of 3 applies. The description adds no parameter-level detail (e.g., that name/agent identify the session) beyond what the schema already provides.

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 ('Starts a run') and even defines what a run is ('a record of one test session'), which an agent can use to tell it apart from sibling tools like finish_run. However, roughly half the text describes sibling tools' behavior rather than this tool's own purpose, which dilutes the focus.

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?

Clearly signals the sequencing: pass the returned run_id to create_address, the waits, count_emails, expect_no_email, check_email and check_out_account, and names finish_run as the closing step. It gives context for when to reach for this tool (start of a test session) but never states when NOT to use it or any prerequisite conditions.

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