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

Annotations already cover the read-only, non-destructive, closed-world safety profile, so the bar is lower. The description adds real context beyond that: it decodes statusCategory values (TRIAGE/BACKLOG/ACTIVE/DONE/CANCELED), explains the experiment/ledger semantics (ledgerEntryId null = no expectation, verdict = confirmed/missed after settlement), and notes scores/anchor are optional. It stops short of listing behavior such as pagination or ordering.

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 description is a single dense paragraph that front-loads a data-model definition rather than the tool's action, and is written in heavy shorthand ('the older lane key in `status`'). Almost every clause carries information, but the structure assumes prior domain knowledge and is not scannable.

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 output schema, the description usefully enumerates the returned fields (statusName, statusCategory, status, ledger fields, scores, workflow anchor). But for a list tool with 0 required params it omits the default scope, ordering, result limits, and what filtering by lane key actually returns, leaving gaps in how to call it correctly.

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 100%, so the schema already documents all three parameters, making 3 the baseline. The description adds only marginal meaning, restating that filtering is by lane key in `status` or workflowPageId and pointing to compass_statuses_list; it does not clarify the enum values (NEW/QUALIFYING/...) mapped to the `status` param.

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 identifies the resource ('the workspace's changes — fixes, chores, new steps, experiments') but never states the verb; the listing action is only implied by the trailing 'Filter by lane key...'. It does not distinguish this tool from siblings like compass_changes_upsert or the other compass_*_list tools, so an agent must infer the read/list role from the title alone.

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 one concrete usage hint — filter by lane key in `status` or by `workflowPageId` — and routes the agent to compass_statuses_list for status names. However, it never states when to use this list versus create/update/set_status siblings, nor what happens when no filter is supplied (all opportunities? default scope?).

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