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

Even though annotations already declare readOnlyHint, idempotentHint, and destructiveHint, the description adds substantial behavioral detail: the exact cannibalization algorithm, the maximum of 200 keywords, the deterministic suggestion logic, the prerequisite of a recent sync, and the non-silent handling of a missing Search Console connection. This goes well beyond the annotations and helps the agent predict side effects and edge cases.

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 long but densely informative; every part relates to correct invocation or interpretation. It front-loads the core purpose before elaborating on the algorithm, output fields, prerequisites, and alternatives. It could be slightly more scannable with structural breaks, but it avoids fluff and repetition.

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 tool with this complexity, the description covers prerequisites, input semantics, output shape, edge cases, and alternatives. It even explains the meaning of different suggestion reasons and how scheduled articles are represented. The presence of an output schema helps, but the description still independently supplies enough context for an agent to invoke and interpret results correctly.

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%, with each parameter already documented. The description adds marginal context by explaining include_planned's effect and the website_id requirement for multi-website accounts, but most of this is a paraphrase of the schema. The added 'best position first' ordering note is useful but not substantial enough to push above baseline.

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, specific action: 'Finds tracked keywords for which two of the site's own pages will compete.' It defines the resource (tracked keywords) and the exact outcome, and it explicitly differentiates from Search Console's definition and from sibling tools like get_keyword_rankings. There is no ambiguity about what this tool produces.

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 states concrete when-to-use conditions: it requires a recent Search Console sync, ignores snapshots older than 30 days, and returns a message when Search Console is not connected. It also names alternatives explicitly: 'Not a rank tracker: use get_keyword_rankings for positions and get_keyword for one keyword's articles.' This gives the agent clear routing guidance.

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