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

Annotations already declare readOnlyHint/openWorldHint=false, but the description adds genuinely non-obvious behavior on top: the tool 'opens nothing by itself' and its output is procedural guidance (screens, buttons, fields) rather than CRM data. It also discloses the integration route (Cloud Browser + browser tools) and the absence of an official MCP server. The only gap is that it never says what the returned text looks like or whether any opportunity data is included.

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 core behavior is front-loaded, but the middle is a run-on that mixes three ideas (what it returns, that it opens nothing, and which tools to use next) in a single breathless sentence. The trailing API-availability trivia ('checked 20 Oct 2026') is peripheral to calling the tool and reads as 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?

With no parameters, no output schema, and rich annotations, the description is close to sufficient, but it leaves an important ambiguity unresolved: whether the response contains any actual opportunity records or purely navigation instructions, and how a 'list opportunities' request should be sequenced with sibling tools like copper_crm_list_pipelines. Adequate for a first call, not complete for deciding between routes.

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 the schema carries no semantics to supplement; baseline 4 applies. Nothing in the description misleads about inputs, though the absence of any note about filtering (e.g., by pipeline or owner) is consistent with a no-arg schema.

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 opening claim 'List opportunities in the user's own Copper CRM account' describes a data-listing operation, but the very next sentence reverses that: the tool 'Returns how to do it in Copper CRM step by step (screens, buttons, fields) and opens nothing by itself.' An agent can eventually work out that this returns a how-to guide rather than opportunity records, but the first sentence points at the wrong resource/action, so the actual purpose is only recoverable mid-paragraph and is not differentiated from the sibling cotlet_app_guide.

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 does give an explicit two-step workflow: call this to get step-by-step instructions, then 'do it with the cotlet_browser_* tools in the user's Copper CRM Cloud Browser.' That is clear routing to the relevant siblings. It stops short of saying when not to call it (e.g., when the user just wants data returned directly) or how it compares to cotlet_app_guide.

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