analyze_code_impact

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

No annotations are supplied, so the description carries the disclosure burden; it does tell the agent the scope of results (all callers, dependents, references) and implicitly that this is a read-only analysis. It omits whether the workspace must be indexed/scanned first, whether results are cross-service, and any performance or size characteristics of the blast radius.

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?

Two sentences, front-loaded with the result set the caller gets, and the prioritization note is short. No filler, though the parenthetical type list duplicates the schema.

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 two-parameter tool with no annotations and no output schema, the description covers what is being computed but not the shape of the returned data or its ordering/grouping. Adequate to select the tool, thin for interpreting the result.

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%, so both parameters are already documented in the schema, and the description's enumeration of symbol kinds (Class, Interface, Function, Service, Table) merely echoes the symbolName field description. No additional meaning is added about workspacePath or about which symbol reference form to use.

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?

States a specific analysis verb (blast-radius impact analysis) plus the concrete outputs: callers, dependents, and references affected by modifying a symbol, with the symbol kinds enumerated. It stops short of distinguishing itself from close siblings such as get_callers or get_call_chain, which overlap on 'callers'.

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?

'Prioritize over grep' is an explicit preference directive that tells the agent to reach for this instead of text search, which is genuine guidance. However, there is no when-not condition and no routing advice toward the more granular sibling tools (get_callers, get_call_chain, get_affected_tests) that cover parts of the same ground.

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