read_card

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

With no annotations, the description must carry the full burden. It does well by disclosing the expensive nature (network- and token-intensive) and the scope of data fetched (full content, all comments). It does not detail pagination, rate limits, or failure behavior, but the cost disclosure is a strong and operationally useful behavioral trait beyond the schema.

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?

Three sentences with zero waste. The first sentence defines the resource and return fields, the second carries the critical cost warning with a clear directive. The warning is front-loaded appropriately, giving the agent immediate operational guidance.

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 tool with three simple required parameters, the description covers the core purpose, return content, and cost implications. It doesn't mention pagination (if any), rate limiting, or that 'number' could be an issue number or PR number, but the output schema is absent, and the description does a reasonable job of covering the main concerns for an agent deciding to call 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?

The schema description coverage is 0%, so the description must compensate. It mentions the three parameters (owner, repo, number) implicitly by noting 'one card/issue' and the field list. However, it does not explain that owner is the GitHub account, repo is the repository name, or that number is the numeric issue/card ID. The schema itself provides no descriptions, so the description provides some context but not complete parameter semantics.

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 clearly states that the tool reads the full content of one card/issue, specifying the exact fields returned (title, state, body, milestone, comments) and the unique identifier parameters. This distinguishes it from sibling tools like read_milestone and read_project by emphasizing it's for a single card/issue with full content.

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 warns that the operation is network- and token-expensive, and advises avoiding unless asked or necessary. This provides clear usage context for when to invoke this tool. However, it doesn't explicitly name alternative tools (e.g., a lighter-weight list tool) for cases where full content isn't needed, though the cost warning serves a similar purpose.

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