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

Annotations declare destructiveHint=true, and the description earns that: it discloses that `rules` REPLACES the entire list, that changing rules reassigns pages immediately in every report, that nothing is recomputed or stored, and how uncompilable vs. skipped/ReDoS-prone regexes are treated and surfaced via `ruleWarnings`. That is deep behavioral context well beyond the annotation flags.

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?

Front-loads the purpose, then patch semantics, then the destructive rules-replacement warning and regex caveats. Four dense sentences with no filler; slightly long, but each sentence carries actionable information.

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 mutation tool with an output schema already covering return values, the description supplies everything an agent needs: which fields are mutable, patch vs. replace semantics, the irreversible reassignment consequence, and the warning-relay obligation. No material gap remains.

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 only 20%, so the description must carry weight, and it does: it explains patch semantics for all mutable fields and gives rich semantics for `rules` (full replacement, no stable ids, replacement shape) and for regex validity outcomes. It adds little for `groupId` or the color format, which remain inferable only from the schema.

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 verb+resource ('Edits an existing content group') and immediately enumerates the mutable fields (name, description, color, matching rules). This is distinguishable from siblings list_content_groups, create_content_group, and delete_content_group 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 partial-update guidance ('Only the fields you pass change; omit a field to leave it untouched') and names an alternative tool plus the condition that selects it ('read the current rules with list_content_groups first if you mean to add one'). It stops short of explicit when-not-to-use or prerequisites, so it is strong but not exhaustive.

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