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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavior beyond that—pagination continuation via offset and fuzzy spelling matching—but it silently ignores the write-shaped parameters (keep, rows, newName) that exist in the schema, leaving the agent to wonder whether they do anything given action is limited to 'list'.

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 sentences, front-loaded with the primary list operation followed by the optional filters. Nearly every sentence carries an instruction, though the trailing 'Set action to one of: list' is redundant given the single-value enum in the schema.

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 9-parameter tool with no output schema and 11% schema coverage, the description should account for the remaining parameters. Presence of keep, rows, and newName—write-shaped arguments on a read-only tool whose only permitted action is 'list'—is a real hazard that the description neither explains nor warns about, and no return shape or pagination limit is mentioned.

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 description coverage is only 11%, so the description must compensate; it explains name/names (spelling matching), unusedOnly (unused filter), offset (pagination), and action (only 'list'). That leaves keep, rows, newName, and the array-of-objects shape of rows completely unexplained, and 'company' is covered only because its own schema description happens to be detailed.

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 states a specific verb+resource ('List payees') and distinguishes two modes: full listing for the active company vs. fuzzy matching by 'name' or 'names'. It also clarifies that the 'action' enum has exactly one member ('list'), which resolves the ambiguity created by the mutation-sounding tool name 'manage_payees'. It does not differentiate itself from any sibling tool, so it stops short of 5.

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 conditional guidance for three parameters: set unusedOnly=true for unused payees, use offset to continue a paginated list, and use name/names for spelling-match lookup. However, it never says when to choose this tool over siblings such as list_companies or manage_transactions, and it does not state the default behavior when no filter is given.

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