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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, and the description reinforces rather than contradicts them by saying the tool opens nothing by itself and only returns instructions. It adds real behavioral context beyond annotations (returned content is screens/buttons/fields, plus the note that Procore ships no MCP server), though it omits preconditions such as whether a Cloud Browser session must already be open or authenticated.

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 operative sentences are front-loaded and efficient, but the trailing note about Procore's REST API, OAuth 2.0, sandbox and a dated 'checked 5 Nov 2026' audit is justification rather than invocation guidance and occupies nearly a third of the text. The parenthetical screens/buttons/fields detail is useful; the vendor-API aside is not.

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 instruction tool with no output schema, the description covers what comes back (step-by-step Procore UI guidance) and what to do next. It stops short of the operational prerequisites an agent needs, such as whether a Cloud Browser session or Procore login is required before calling.

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 cannot carry meaning and the baseline of 4 applies. The description correctly implies no inputs are needed, though it never explicitly says the tool is parameterless or that intent must be conveyed in natural language elsewhere.

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 name and first clause state a clear verb and resource (create an observation in Procore), but that clause alone is misleading since the tool does not create anything; the second clause corrects it by stating it returns step-by-step Procore instructions and 'opens nothing by itself'. It does distinguish itself from the cotlet_browser_* family by naming them as the execution path.

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?

The usage flow is explicit: call this to get the Procore steps, then perform the action with the cotlet_browser_* tools in the user's Cloud Browser. It does not state exclusions (for example, when to prefer a direct API path or how it relates to procore_create_rfi for other record types), so it falls short of full when/when-not coverage.

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