get_symbol_context

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

Without annotations, the description discloses the 5-caller/callee limit and compactness for context windows. It does not explicitly state that the tool is read-only or non-destructive, but the nature of the operation suggests safety. The description provides key behavioral boundaries.

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 two sentences, directly stating the output and design intent. Every sentence adds value; no filler or repetition. Information is front-loaded with the core action.

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 no output schema, the description adequately covers the return content (body, signature, callers, callees). It does not specify the format or structure, but the tool's 'rich LLM context' purpose makes this acceptable. The limits are mentioned, adding completeness for usage.

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 100%, and the description adds meaning to the 'name' parameter by listing what is returned (body, signature, up to 5 callers/callees). For 'project_root', it notes auto-detection, augmenting the schema's null default.

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 returns body, signature, callers, and callees of a symbol. It differentiates from siblings like find_callers (returns only callers) and explain_symbol (likely natural language) by offering a combined snapshot for quick context.

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 positions the tool as 'rich LLM context' that answers about function and fit, implying use when needing a compact overview. However, it does not explicitly state when not to use or mention alternatives like deeper analysis tools, leaving some implicit inference to the agent.

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