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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuine behavioral context beyond that: watch-only mode is explained as recording intent without touching comments, and it notes that AI-dependent rules become inert once the AI allowance is exhausted, which is a non-obvious operational constraint an agent would otherwise miss.

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 opening clause states the scope immediately and the usage phrases are tacked on at the end, so it is front-loaded. The first sentence is a long comma-separated enumeration that is dense but each item is a real returned field, so little is wasted; only slight trimming of the field list would tighten it.

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 correctly carries the burden of describing the return shape, and it does so thoroughly with the enumerated configuration fields. The one material gap is the account-fallback behavior, where description and schema disagree, leaving the agent unsure whether omitting the id returns one account or all accounts.

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 the parameter is fully documented, so the baseline would be 3. However, the description's statement that omitting the account 'answers for the workspace's first connected account' directly conflicts with the schema description, which says leaving it out 'covers every account in the workspace.' This contradiction adds confusion rather than meaning, so it scores below 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 names the exact resource (Comment Guard configuration for one Instagram account) and enumerates the concrete fields returned: on/off state, watch-only mode, AI rule enablement and confidence threshold, protected users, allow lists, per-rule action and enabled flag, plus the AI allowance. This level of detail cleanly separates it from guard_settings_update (writes), guard_rules_* (rule CRUD) and guard_recent_decisions (decision log) 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?

It supplies three natural-language trigger phrases ('is Comment Guard on', 'what is it set to do', 'why did it not catch this') and states the no-argument behavior, which is solid context for selecting the tool. It stops short of explicitly naming alternatives or when-not-to-use conditions (e.g. 'use guard_recent_decisions for the actual decision history'), so it is clear but not fully routing.

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