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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds extensive behavioral context beyond annotations: supported operators, boolean field special-casing, criteria structure, and sort field semantics. This goes well beyond what the annotations convey and tells the agent how the query behaves and how to construct valid requests.

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 well-structured with clear labeled sections and front-loaded purpose, making it easily scannable. It is longer than minimal, but the extra sections are dense and actionable, covering use cases, exclusions, criteria construction, operators, boolean handling, and sort options without seeming padded.

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 complex tool with six optional parameters and no output schema, the description is impressively complete: it covers use case selection, alternatives, criteria building, operators, boolean fields, and sort options. The only notable gap is the absence of any description of the response shape or pagination behavior, which would help an agent consume the results, especially since no output schema exists.

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 baseline is 3. The description goes further by explaining how to build the criteria object, listing all operators, giving a boolean field example, and describing the sort format (field,direction) with its default. This adds meaningful semantic depth beyond the raw schema, though some of the content overlaps with the schema's enum and property descriptions.

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 opens with a clear verb and resource: 'Query account journey insights with filtering, sorting, and pagination.' It distinguishes itself from get_account_summary_insights by explicitly stating 'DO NOT USE FOR: Single account lookup' and naming the alternative, so an agent can tell them apart without opening schemas.

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 'USE FOR' and 'DO NOT USE FOR' sections give explicit positive and negative usage guidance, and directly name the sibling tool for single account lookup. It also provides a concrete multi-step workflow for creating audiences and building criteria, which clarifies exactly when and how this tool fits into a larger task flow.

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