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

Annotations already declare read-only, idempotent, non-destructive and closed-world behavior, so the bar is lower. The description still adds useful traits the annotations do not: a maximum of 10 results and a ranking preference favoring real recordings. It says nothing about behavior when the situation string is unmatched or ambiguous, which is the main remaining gap.

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 sentences, both front-loaded with the actionable information (when to call, where the input comes from, what comes back). No filler and no repetition of schema or annotation content.

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 simple two-parameter read tool with an output schema and full annotations, the description covers trigger, input source, result cap and ordering. Only failure/ambiguity handling for an unrecognized situation is left unaddressed, a minor omission given the existing structured fields.

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 only 50%: the situation parameter carries its own description, while limit has no prose beyond bounds. The description partially compensates by stating the result cap ("up to 10 phrases"), which explains the limit ceiling, but it does not explain why or when to lower it.

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 action (return Emirati phrases) tied to a specific resource (a situation id or title), with concrete examples of situations. It also names list_situations as the source of the input, so the agent can tell it apart from that sibling, though the distinction from search_phrases/get_phrase is only implicit.

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?

"Use this when the user wants Emirati phrases for a situation" gives a clear trigger condition and example domains (doctor, pharmacy, directions). It also encodes a prerequisite workflow by pointing at list_situations for the id/title, but it never states when to prefer search_phrases instead.

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