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

The annotations already convey that the tool is not read-only, not idempotent, and destructive. The description adds meaningful behavioral context by specifying that it 'consumes 5 CalmSEO credits' and that it 'avoids full-site crawl task queues', which explains the resource impact and execution model beyond what annotations offer. It does not contradict the annotations.

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 compact sentences, each carrying essential information: the core function and the key distinguishing constraints (avoids full-site crawl, consumes 5 credits). There is no redundancy or filler. The main purpose 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?

For selection and invocation, the description is sufficient: it identifies the input (URL), the cost, and the execution context. However, there is no output schema and the description does not indicate what kind of audit report is returned or how the results are structured. An agent would need to discover the output format after calling or rely on separate documentation. Given the tool's moderate complexityholistic, this is a notable gap.

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 60%; the boolean parameters are well-described in the schema, and the description clarifies the sole required parameter (`url`) by emphasizing 'Single URL'. However, the `accept_language` parameter remains undocumented in both schema and description, and the description adds no further parameter-level guidance beyond what the schema already provides. This is adequate but not exceptional.

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 a specific action ('on-page SEO audit') on a specific resource ('Single URL') and identifies the underlying service ('DataForSEO Instant Pages'). It distances itself from 'full-site crawl task queues', which differentiates it from a broader audit workflow and from the unrelated sibling tools (keyword, GSC, SERP tools). This is unambiguous and immediately distinguishes the tool's purpose.

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 clear context for when to use the tool: for a single URL audit, avoiding the overhead of a full-site crawl. It also mentions the credit cost, which is relevant for decision-making. However, it does not explicitly name an alternative tool or state 'use X instead', leaving the contrast with a full-site crawl tool implicit rather than explicit.

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