sage_call

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

With no annotations provided, the description fully addresses behavioral aspects. It clearly states: 'Side effects are exactly the side effects of the command itself,' and lists the return fields (exit_code, compact output, run_id, purpose, agent metadata). This gives the agent a complete understanding of what to expect and the risks involved.

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 concise (about 60 words over three sentences) and front-loaded with the core action. Every sentence provides essential information: the main function, when to use it, what it returns, and safety warnings. There is no redundancy or extraneous 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?

Given the absence of annotations and output schema, the description is remarkably complete. It covers purpose, usage guidelines, behavioral traits (side effects), return values, and security warnings. This is sufficient for an agent to correctly invoke and understand the tool's behavior without needing additional context.

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 input schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds minimal additional meaning beyond the schema: it mentions the purpose label and lists categories (read, search, test, etc.), which are already enumerated in the schema. The only extra is noting that purpose 'improves ML failure prediction.' Thus, the description adds limited value over the schema.

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 the tool's primary function: 'Run one local shell command through SAGE with a purpose label.' This provides a specific verb (run) and resource (local shell command), and the mention of SAGE and purpose label distinguishes it from sibling tools like sage_explain_error or sage_suggest_fix, which handle error explanation and fix suggestions rather than direct command execution.

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 states when to use the tool ('Use when you need command execution and want the result categorized') and when not to use it ('Do not use for secrets, credential prompts, or deployment unless explicitly requested'). This provides clear usage boundaries and alternative considerations, aiding the agent in correct selection.

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