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

Annotations already declare a safe read (readOnlyHint=true, destructiveHint=false, idempotentHint=true), yet the description adds meaningful behavior beyond them: the brief is derived only from the page and its Search Console data, it must be applied in the site's own CMS, and it enumerates the sentinel error values not_accepted and blawgy_post. That is real context about state dependency and output shape, not restatement of 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?

Effectively three sentences, each carrying distinct load: what the brief contains, when it is available, and what to do afterwards. The first sentence is heavily nested with parentheticals and runs long, but the key precondition and postcondition are front-loaded rather than buried.

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?

There is no output schema, so the description carries the full burden of describing the return value and it does: the brief's four components plus the two inline sentinel results. With preconditions, CMS application context, and the mark_refresh_done follow-up all covered, nothing material is missing for a two-parameter read tool.

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% and both parameters are documented, so the baseline is 3. The description goes further by tying refreshId back to its origin (suggestionId / refreshId in get_plan) and framing the page-type precondition, which helps the agent locate the correct id. It does not document the site parameter's format, so it stops short of a 5.

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 artifact (an update brief) for a specific resource (a page refresh Blawgy did not write) and enumerates its contents: summary, page steps, keywordsToAdd, and what to keep. It also scopes the case with refreshOwnerKind "page" and explicitly separates itself from the Blawgy-authored smart-update path, so an agent can distinguish it from get_research_brief and list_update_opportunities without opening any schema.

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?

Gives explicit preconditions (works once the refresh is accepted via accept_plan_suggestion, or when it fills an open slot) and explicit failure/alternative routing (returns not_accepted for a merely suggested refresh; blawgy_post for a Blawgy-authored page, pointing to list_update_opportunities). It also names the required follow-up tool, mark_refresh_done, which is exactly the when/what-next guidance an agent needs.

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