Analyze a post

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: the comparison is scoped to same-format recent posts, and the returned payload changes shape depending on whether an AI provider is configured (diagnosis + next steps vs. a plain brief). That conditional output behavior is exactly what an agent needs and is not derivable from the annotations. It omits rate limits and the fact that account context/auth must be in place.

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?

A single front-loaded sentence that leads with the comparison being made, then the metric list, then the AI-dependent output contract. The colon-and-list construction is dense but earns its words. Slightly long for one sentence; could be split for scanability.

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?

With no output schema, the description usefully enumerates the return payload and its conditional AI branch, which is the main complexity here. Four params with only 50% coverage and no mention of account selection or the baseline_posts meaning leaves a small gap, but an agent could call this correctly from the description plus 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 50%: account and diagnose are documented in-schema, while media_id and baseline_posts carry no description. The description partially compensates by explaining that comparison is against 'your own recent posts' (implying the baseline concept) and by tying the AI provider to the diagnose flag, but it never states what baseline_posts controls or what happens if media_id points to a different format. Baseline 3 is appropriate.

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 opens with a specific verb and resource: per-post (reel/story) performance measured against the account's own recent posts of the same format, and it enumerates the concrete metrics (outlier score, engagement rate, saves+shares per viewer, watch time, skip rate). That is far more than a restatement of the name. It stops short of naming the siblings it competes with (get_media_insights, find_outliers), so sibling differentiation is implied but not stated.

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?

Usage is implied rather than prescribed: the reader can infer this is for judging one specific post relative to the account's baseline. There is no explicit when-to-use, no 'use find_outliers instead for a set of posts' exclusion, and no mention that it requires a connected account. The AI-provider-vs-not sentence is behavioral, not a routing cue.

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