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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows this is a safe read operation. The description adds critical behavioral context: it discloses that QuickBooks has no OR support, that filters are ANDed, that field names/values are case-sensitive, that government identifiers/birth dates/card-processing details are unavailable, and that one call returns at most 1000 records with truncation. This is rich behavioral disclosure beyond what annotations provide.

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 the core purpose ('Search credit memo records in QuickBooks Online') before diving into criteria details. Every sentence adds value, but the criteria explanation is quite long and could benefit from slight restructuring (e.g., bullet points or separation of pagination from filter syntax). Still, it is appropriately sized for the complexity of the tool and contains no filler.

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 search tool with no output schema, the description covers everything an agent needs: what it searches, how to filter, what limitations exist, pagination behavior, and what happens when criteria is omitted. The annotations cover the safety profile (read-only, non-destructive). The only minor gap is that it doesn't describe the exact return shape, but for a search tool with no output schema, the description's coverage of behavior and constraints is comprehensive.

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 100%, so the schema already documents both parameters. The description adds significant meaning beyond the schema: it explains the criteria parameter's flexible formats (array of {field, value, operator}, simple object, or {criteria, asc|desc, limit, offset, count}), lists valid operators, gives example filterable fields, and explains pagination semantics. The company parameter is also clarified as optional when only one company is connected. This goes well beyond the baseline 3 for full coverage.

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 clearly states the tool's function: 'Search credit memo records in QuickBooks Online.' It uses a specific verb ('Search') and resource ('credit memo records'), and the title reinforces this. It distinguishes itself from sibling tools like get_credit_memo (which retrieves a single record) and create_credit_memo (which creates), so an agent can easily tell them apart.

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 description provides extensive usage guidance: it explains the criteria parameter formats, operators, filtering limitations (no OR, no Line fields, only top-level fields), case sensitivity, and pagination behavior. It explicitly states what to do when needing more than one page ('narrow with filters or walk it with limit and offset') and what happens if criteria is omitted. This is far beyond a simple 'when to use' statement and gives the agent clear decision-making rules.

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