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 context: the not-found error string, the fact that only collection metadata is returned, and an untrusted-input warning for user-generated content. The safety profile is well covered, though auth/permission requirements are not mentioned.

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-loaded with the action and identity, followed by return fields, scope limitation, error behavior, and a security note. Every clause carries information; no filler.

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 enumerates the returned fields, states the error case, clarifies what is NOT returned, and flags untrusted content. An agent has everything needed to call and interpret it.

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 100% for the single parameter, so the baseline is 3. The description mainly lists return fields rather than clarifying the parameter; the pk provenance note ('from get_user_highlights') adds modest value but the schema already handles the parameter.

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 ('Get one Instagram story highlight by its ID (pk)') and scopes it further by enumerating the returned fields. It is clearly distinguishable from get_user_highlights (which supplies the pk) and get_story_by_id (stories vs. highlights).

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 a clear condition for use ('Use it for a pk from `get_user_highlights`') and an explicit scope exclusion ('Returns collection metadata only, not the stories inside'). It stops short of naming the alternative tool for retrieving the contained stories, so the when-not is implied rather than routed.

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