Threads insights

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial behavioral context beyond that: the unknown-metric refusal behavior, the metric set differences, the lifetime-metric window behavior, the demographics floor of 100 followers, and the clarification that an absent demographics block means under Meta's floor rather than empty audience. This is rich, useful transparency that helps the agent anticipate tool responses.

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 description is long but every sentence is necessary and dense with useful information. It front-loads the primary purpose, then adds edge-case behaviors and constraints. There is no fluff – each clause adds value, making it efficient given the complexity it covers.

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 read-only analytics tool with no output schema, the description is remarkably complete. It covers scope logic, metric differences, window behavior, error handling (refusing unknown metrics), demographic floor, and the meaning of absent blocks. Nothing an agent needs to invoke it correctly is missing.

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 each parameter has a description, but the tool description adds significant cross-parameter meaning: how postId determines scope, that since/until only apply to account scope, that breakdown is required by follower_demographics and must be exactly one, and that metrics lists differ between scopes. This goes well beyond the schema's individual descriptions.

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 states exactly what the tool does: 'Performance for ONE Threads post ... or for the whole ACCOUNT when it is omitted.' It lists concrete metrics (views, likes, replies, reposts, quotes, shares, clicks, followers_count, follower_demographics) and explicitly distinguishes the two scopes, clearly differentiating it from siblings like instagram_insights or meta_post_insights.

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?

The description gives explicit guidance on when to omit postId (account-level), notes that metric sets differ by scope, explains that since/until narrow only the account window, and warns that followers_count and follower_demographics are lifetime metrics that ignore the window. It also clarifies that an unknown metric is refused by name, preventing misuse. While it doesn't name alternative tools, it fully specifies its own usage conditions.

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