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

With no annotations, the description does the heavy lifting: it states a person reads every report, that nothing is executed automatically, and that proposed solutions are treated as unverified suggestions — key facts an agent cannot get from structured fields. It also warns against including secrets or personal data. It stops short of saying what the call returns or whether the report is attributable/anonymous beyond contact_email, which is the only real gap.

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 sentences, front-loaded with the action, then triggers, then report-quality guidance, then the privacy caveat. It is longer than a data-retrieval tool needs, but for a free-text reporting tool every sentence adds usable instruction and there is no 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 10-parameter, nested-object, no-annotation, no-output-schema tool, the description covers purpose, timing, review process, and privacy adequately but leaves the enum fields, the agent object, and the response behavior (confirmation? report id?) unexplained. It is serviceable but not complete enough to remove all guesswork.

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 only 30% across 10 parameters, so the description carries real weight — and it does clarify the intent of what_i_tried, what_happened, expected and proposed_solution ('treated as unverified suggestions'), plus privacy guidance that applies to the free-text fields. However, it says nothing about kind, severity, tool, agent (e.g. whether to self-identify), or when contact_email is warranted, all of which remain undocumented.

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 opens with a specific verb and recipient: 'Tell the IRIS team how this went', plus an enumeration of the content expected (what you tried, what happened, what you expected, how you would fix it). That is unmistakably distinct from every sibling, which retrieves market/venture data rather than reporting back to the team.

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?

Trigger conditions are explicit: 'after any call that failed, returned something unusable or surprising, or worked especially well', plus a separate case for improvement ideas. It leaves little room for an agent to misjudge when to call it, and it implicitly excludes routine successful calls that need no comment.

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