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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description goes well beyond that with a real behavioral contract: a 15-minute provenance_token window usable on any replica, the unverified_model_data fallback, mandatory verbatim attribution footers, and a data-accuracy rule forbidding invented metrics. It omits error handling, rate limits, and pagination behavior.

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?

Purpose is stated first, but the bulk of the text is cross-tool policy about chart_render provenance, attribution footers, and a generic data-accuracy contract that is not specific to this connector. For a 7-action read-only SEO tool, the description is over-weighted toward ecosystem boilerplate at the expense of tool-specific detail.

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?

With annotations covering safety and no output schema, the agent still needs to know what each action returns and how pagination/limits behave; the enum descriptions cover returns only partially and appear cut off. The provenance and accuracy rules are complete, but core call mechanics for a 7-action dispatcher are only minimally addressed.

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% and the params field already enumerates action-specific keys for all seven actions, so the burden is on the schema, not the description. The description adds no parameter syntax, defaults, or ordering guidance, and several enum descriptions appear truncated mid-sentence, which is a schema issue rather than a description one.

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 first sentence names a specific platform and enumerates resources it covers (domain overview, organic/paid keywords, competitor analysis, backlinks, keyword research), and the action enum names each operation. However, it never distinguishes this connector from close siblings such as ahrefs_connector, search_console_connector, or semrush_dashboard, leaving the agent to infer which SEO surface to pick.

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 only conditional guidance concerns a different tool ('when the user asks for a visual... call chart_render'). There is no statement of when to use semrush_connector versus its SEO siblings, no prerequisites, and no exclusion criteria. The agent must infer applicability from the platform name alone.

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