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

With no annotations, the description carries the full burden and does disclose key traits: 'Read-only' declares the safety profile, 'Only threads of the API key's user' declares the auth/scope boundary, and 'plus counters by status and sentiment' hints at the return shape. It stops short of pagination behavior or return-format details, keeping it from a 5.

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?

Two dense sentences with the resource and filters front-loaded and the scope/read-only constraints appended. Efficient with little waste, though slightly packed with enum lists.

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 5-param filtered-list tool with no output schema and no annotations, the description covers purpose, filters, counters, scope, and read-only status well. Pagination semantics are the only notable gap, handled by the schema.

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 60%. The description reiterates the status and sentiment filter values (which the schema already enumerates) but does not mention limit/offset or add syntax beyond the enums, so it adds only marginal value over the schema. Baseline 3 fits.

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 (conversations/threads the AI is handling for a campaign) and includes scope and counters. It is clearly distinguishable from get_campaign_thread (singular single-thread fetch), though it doesn't explicitly name sibling alternatives.

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?

Implies usage through the filter options (status/sentiment) and scope ('Only threads of the API key's user'), but never states when to use this versus get_campaign_thread or list_campaign_replies, nor any exclusions.

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