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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds real context beyond that: results are tenant-scoped, the assignedToMe filter is stage-specific, and each record carries an `entityDetails` object describing the linked lease or contract. Remaining gaps are pagination, default/max page size, and sort order.

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 sentences are front-loaded and earn their place, but the payload is padded with template boilerplate ('GET /api/approvals. Operation ID: e70dd9642ffd2dec231cef2d') and a stray double period. The operation-ID string adds operational noise rather than invocation guidance.

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 does partially compensate by describing the entityDetails payload, and it explicitly routes the agent to describe_operation for the real request schema. But for a filtering-heavy list endpoint whose input schema is an opaque object, an agent still lacks the filter vocabulary needed to invoke it without a second tool call.

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 0% and the `query` parameter is an unconstrained free-form bag, so the schema provides no help at all. The description rescues one parameter by explaining `assignedToMe` semantics and points to describe_operation for native request schemas, but the other available query fields (status, entity, date, paging) remain undocumented.

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?

States a specific verb and resource ('List approvals', 'Returns approval records for the tenant') and defines the tenant-wide scope. It does not differentiate itself from close siblings such as get_approvals_by_id, get_approvals_progress, or get_approvals_condition_fields, leaving the agent to infer the boundary.

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?

Gives one concrete usage instruction — 'Use `assignedToMe=true` to restrict to approvals where the calling user is an approver on the current stage' — which is genuinely actionable. However, it never states when NOT to use it or names an alternative sibling (e.g., fetching a single approval by id), and there is no guidance on pagination, defaults, or other filters.

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