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

Adds value beyond readOnlyHint=true/destructiveHint=false by disclosing a return-behavior detail: results carry SyncToken and are full records, so no follow-up get is needed. It also exposes the Id IN bulk-read pattern. It does not cover pagination/limits in the description, but those are handled thoroughly in the schema.

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?

Two sentences, no filler. The resource is stated first and the high-value behavioral note (full records, SyncToken, no get needed) is front-loaded.

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?

The description covers the essential usage scenario and return-completeness for a search tool, and the schema fully covers parameter semantics and pagination. No output schema exists, but the description states results are full records with SyncToken, which is the key return-value detail an agent needs.

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% and the criteria description already details operators, ANDing, 1000-record page limits, and offset/limit. The description only restates the Id IN pattern, adding marginal value. Baseline 3 is appropriate.

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 ('Search') and resource ('invoice records') with the target system ('QuickBooks Online'). It distinguishes itself from get_invoice by explaining search returns full records, and from get_open_invoices by implying arbitrary criteria.

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?

Explains when to use search over get ('no get is needed after') and gives a concrete pattern ('read several known Ids in one search with Id IN'). However, it doesn't name sibling alternatives like get_invoice or get_open_invoices explicitly, nor does it state exclusions.

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