code_graph_suggest

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces the read-only nature. It adds valuable behavioral context beyond annotations: the ranking is based on 'keyword overlap with symbol names + file paths' and explicitly excludes embeddings and LLM, informing the agent about the lexical, non-semantic nature of the tool. This context helps the agent set appropriate 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 two sentences, remarkably concise with no fluff. It front-loads the core purpose, then adds the method and a critical differentiator. Every sentence earns its place, and the structure makes it easy to scan and extract the key purpose and constraints.

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 lacks an output schema, so the description should at least hint at return value characteristics, which it does not. While it clarifies the core purpose and read-only nature, it omits parameter explanations (especially app_id and db_path) and doesn't mention output format or behavior details like pagination or error handling. Given the tool's relative simplicity, some aspects are adequately covered, but the parameter ambiguity and lack of output information leave gaps.

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 description coverage is 0%, so the description must compensate for parameter meaning. It only vaguely references 'task description,' which maps to the 'task' parameter, but it provides no explanation for 'app_id', 'db_path', or 'max_results'. The description fails to clarify these parameters, leaving the agent to guess their purpose, especially since the schema offers no hints. This is a significant gap given the zero coverage.

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 suggests files most relevant to a task description, with a specific ranking mechanism (keyword overlap with symbol names and file paths). It also distinguishes itself by explicitly noting 'No embeddings, no LLM', which sets it apart from sibling tools like code_graph_search or code_graph_explain. The verb+resource structure is precise and unambiguous.

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 implies usage context by highlighting that it avoids embeddings and LLMs, suggesting a fast keyword-based approach. However, it does not explicitly name alternative tools or state when to use this versus others among the many code_graph siblings. There is no direct 'when-to-use' or 'when-not-to-use' guidance, only an implied niche.

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