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

Annotations already cover read-only and idempotent safety. The description adds valuable behavioral context beyond annotations: it lists what the metadata contains (field schema, record count, description) and the recommended sequencing relative to query, which helps the agent set expectations.

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 one sentence with a dash separating the main action from the usage note. Every word adds value, and the key point 'call before query' is front-loaded. No wasted phrasing.

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?

The tool has a single parameter, full schema coverage, and annotations that define safety. The description explains what is returned and when to call it relative to query. It does not explicitly mention the response format, but for a low-complexity read-only metadata tool this is adequate.

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?

The single parameter dataset_id is fully documented in the schema, including its source ('from search_datasets'). The description reinforces the purpose but adds little meaning beyond the schema, so a baseline of 3 is appropriate when schema coverage is 100%.

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 a specific verb ('Get'), resource ('metadata for one Bahrain government open data dataset'), and details what is included (field schema, record count, description). It also distinguishes the tool from siblings like query and search_datasets by framing it as a pre-query step to learn column names.

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 explicitly says 'call before query to learn the column names,' which gives a clear usage time. It does not explicitly name alternative tools or when-not-to-use, but the context is strong enough for an agent to act correctly.

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