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

Annotations already declare readOnly, idempotent, non-destructive and non-open-world, so the safety profile is covered. The description adds one genuinely useful behavioral fact beyond them — that the output is instructional content rather than data, and that it touches nothing on its own — but it says nothing about how the instructions are shaped, whether they are deterministic for the same request, or what the agent should do if a step fails. Consistent with annotations, so no contradiction.

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 first two clauses are well front-loaded and earn their place. The tail is waste: 'from ChatGPT, Claude or any AI agent' is marketing framing, and the final sentence about Simpro's REST API, OAuth 2.0 coverage and the absence of an official MCP server does nothing to help an agent decide to call this tool or how to call it.

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 zero-parameter, read-only guidance tool with no output schema, the core is present: what it returns, what it does not do, and the next step. However, it never says how to phrase or scope the request without parameters, nor how to recover if the user's browser session or Simpro login is not ready — realistic gaps for a tool whose whole value is the procedure it hands back.

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?

The tool takes zero parameters, so there is nothing to disambiguate and the baseline of 4 applies. The description does not attempt to explain any input, which is appropriate here, though it also never clarifies how the agent scopes the search target (item name, category) given there is no input field for it.

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 names a specific resource (catalogue items in the user's Simpro account) and, crucially, states what the tool actually returns: step-by-step instructions covering screens, buttons and fields. It also clarifies the negative — 'opens nothing by itself' — which corrects the impression created by the verb 'Search' in the name. It stops short of distinguishing itself by name from API-style siblings such as simpro_list_jobs, leaving a little inference work.

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 real workflow guidance: call this to get the procedure, then execute it with the cotlet_browser_* tools in the user's Simpro Cloud Browser, which names the concrete follow-up family. What is missing is an explicit exclusion — nothing says when not to call this (e.g. when a direct query sibling suffices) or what preconditions exist, such as the browser already being open.

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