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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is covered; the description adds the default-action behavior and the fields list returns (status open/written/skipped and provenance). For a mixed read/write tool it still omits whether add is idempotent on a duplicate keyword, what happens to already-written articles when a target is removed, and any required permissions.

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 sentence that front-loads the resource definition, then the default action, then the mutation payloads. No filler, and the parenthetical list of returned fields is dense but each element earns its place.

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 4-parameter, no-output-schema tool with mixed read/write actions, the description covers the default action, the per-action parameter requirements, and what list returns. Missing only the return behavior of add/remove and any org-resolution prerequisite, which are minor gaps given the schema documents org.

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 only 25% (only org is documented), so the description must compensate, and it does: it maps parameters to actions ("add" { keyword, pageType? }, "remove" { keyword }) and marks pageType optional. This per-action conditionality is not expressible in the flat schema, so it adds real value; it still doesn't define keyword format or what pageType values mean beyond the enum.

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?

States a specific resource ("The keywords Seovyn writes for (each becomes an article)") plus the three actions it exposes, so the agent knows it manages a keyword-target list rather than articles themselves. It does not name or contrast any sibling, but the enumerated action set makes it distinguishable from seovyn_list_articles and seovyn_write_article.

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?

Declares "list" as the default action and gives the shape of add/remove payloads, which implies when each is used. There is no explicit guidance on when to remove vs. mark skipped, no prerequisites (e.g. whether the org must be resolved first), and no when-not-to-use note relative to siblings.

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