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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, and the description reinforces those with the concrete claim "opens nothing by itself" — an agent gets an unambiguous guarantee that no state changes in HaloPSA. It also tells the agent what the return payload contains (a step-by-step procedure). It does not discuss caching, freshness of the procedure, or rate limits, so it is not fully rich.

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 essential content (returns a procedure, performs no action, follow up with cotlet_browser_*) is front-loaded and easy to extract, but the closing sentence about HaloPSA's REST API and MCP endpoint is tangential to what this tool does and pads the definition. The sentence is also long and multi-clause, mixing the tool's behavior with external API trivia.

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, non-mutating guidance tool with annotations and no output schema, the agent needs to know what comes back and what to do next — both are covered. The residual gap is that the description does not bound the scope of what "client lookup" means in HaloPSA (search vs. open a client record), so an agent may not know how exhaustive the returned procedure is.

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 with 100% schema coverage, so there is nothing for the description to compensate for. The baseline for a parameterless tool applies, and the description correctly conveys that the invocation is context-free — it targets the user's own HaloPSA account implicitly rather than requiring an account or client identifier.

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 definition names a specific action and resource ("look up client ... in HaloPSA") and then clarifies that it actually returns step-by-step instructions (screens, buttons, fields) rather than performing the lookup. That distinction is important and is stated, though it only arrives in the second sentence after a name/title that implies a live query, so an agent skimming the first clause could misread it as a data-fetching tool.

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 a clear execution path: this tool produces the procedure, then the agent carries it out using the cotlet_browser_* tools in the user's HaloPSA Cloud Browser. That is an explicit handoff to a named alternative family. It stops short of saying when NOT to call it (e.g. when the agent already knows the screens, or should use halopsa_search_knowledge_base instead), so it is strong but not exhaustive guidance.

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