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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered. Beyond that, the description adds two behavioral facts the annotations do not: results are returned newest-first, and the endpoint fails with 501 feature_unavailable while ESCROW_API_ENABLED is off, which lets an agent anticipate a specific failure mode.

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?

Four short, front-loaded sentences with no filler: scope and ordering first, then the filtering hint, then the failure mode. The feature-flag sentence is dense but earns its place by explaining a specific error code.

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 paginated, read-only list tool with no output schema, the definition covers scope, ordering, filtering, and a known error condition. It does not describe pagination traversal beyond the schema's cursor text, but that gap is minor given the schema handles it.

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 67% — limit and cursor carry their own descriptions (clamping, malformed-cursor 400). The description adds only that setting role to payer or payee narrows the set, implying the default is both roles, which is slight value beyond the enum definition.

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 names the resource and its scope precisely: escrows where the caller is either payer or payee, with a stated ordering ('Newest first'). That scope implicitly distinguishes it from get_escrow (single record) and get_standalone_escrow, though no sibling is named outright.

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 'role=payer or role=payee narrows the list' line tells the agent how to narrow the result, and the 501 feature_unavailable note is a genuine when-it-won't-work condition. There is no explicit routing guidance between this tool and get_escrow or get_standalone_escrow, so usage is only implied.

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