Retrieve JevTrace context

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

With zero annotations the description carries the full behavioral burden. It does disclose the retrieval mechanism (TypeScript compiler links) and a token-budget constraint plus a cost comparison ('cheaper than searching and reading files'), which is useful context. However, it omits notable behavior it should flag itself — notably that project-wide tasks silently return a repository map rather than code (only documented in the scopeCheck schema field), and says nothing about error modes or result determinism.

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 compact sentences, front-loaded with the trigger condition, then the output, then the constraint. Every clause earns its place; no filler or restatement of the name.

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 complex 17-parameter tool with no output schema and no annotations, the description adequately covers what the tool returns and when to reach for it, which is the core need. But it leaves the repo-map fallback behavior and the entire tuning-parameter surface unexplained, so an agent cannot reason about anything but the default call.

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 only 12% across 17 parameters, so the description must compensate and it largely does not. It adds real meaning for the one required parameter ('give the task in plain words', 'describe the task' rather than a file/line), but the 16 budget/ranking/limit knobs (maxLeads, contextRanking, reverseFanIn, etc.) get no explanation in either schema or description.

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 verb and resource (retrieve TypeScript-linkage context for a task) and enumerates exactly what comes back: implementing functions plus callers, callees, types and tests. The qualifier 'when a JS/TS task needs code you have not located yet' implicitly separates it from retrieve_from_entry (entry-point retrieval) and discover_entries, so an agent can pick it without opening sibling schemas.

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?

'Use first when ...' gives an explicit ordering cue, and the example queries ('where is X handled', 'change how Y works') define the right context concretely. It also rules out a wrong invocation ('Do not pass a file or line; describe the task'). It stops short of naming the alternative tools or the condition that selects them, so it falls short of a 5.

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