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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses non-obvious behavior: pausing preserves history and costs nothing, switching an engine off keeps its history, and the tool previews by default unless confirm:true is passed. This is exactly the contextual disclosure that helps an agent call a mutation safely.

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?

A single dense paragraph that front-loads the changeable attributes before the operational caveats (history, write actions, preview). Every sentence carries information, though the tag and tracking details duplicate schema text and slight trimming would improve scannability.

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 10 parameters, full schema coverage, and no output schema, the description covers the mutation semantics and the preview/confirm workflow that an agent must understand. It leaves the return value shape unstated, but the preview mechanism is explained both here and in the schema, so nothing critical is missing.

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%, so each parameter already carries a rich description (tags replacement semantics, addTags/removeTags being ignored when tags is given, tracks being the complete set, targetUrl null removal, previewToken validity). The description restates the same semantics at a higher level rather than adding new detail, so the baseline 3 applies.

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 specific verb and resource ('Change tracked keywords') and then enumerates the exact mutations available: pause/resume, replace tags, set target URL, change engines and devices. An agent knows precisely what this tool does. It does not name siblings (add_rank_keywords, remove_rank_keywords, set_rank_schedule) to distinguish boundaries, so it stops short of a 5.

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?

It provides clear operational context: requires MCP write actions, and without confirm:true returns a preview. It explains the effect of pausing (not checked, costs nothing, history kept). It does not state when to prefer this over add_rank_keywords, remove_rank_keywords, or set_rank_schedule, nor does it give explicit exclusions.

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