context_pack

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

With no annotations, the description carries the full behavioral burden, and it does so reasonably well: it reveals that the result is intentionally 'minimal', which categories are included, that unknowns are made explicit, and that the relevance method is identifier/graph-based until concept_search is ready. This gives an agent a genuine sense of what behavior to expect, even if side effects and pagination details are not covered.

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, front-loaded with the tool's core purpose, and every word earns its place. The second sentence adds the key caveat about the relevance engine without unnecessary elaboration.

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 10-parameter tool with no annotations and no output schema, the description is adequate for basic usage: an agent can reasonably call it with just a question and consume the returned factual set. It clearly lists gaps around offsets and result-shape structure and does not mention decision criteria against sibling tools, so it falls short of being complete.

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 10%, so the description must compensate for the many undocumented parameters. The category list (symbols, relationships, conditions, tests, specs, unknowns) maps directly to the six offset parameters, adding real meaning. However, it still leaves the semantics of max_symbols, max_neighbors, and the question parameter implicit, and does not explain pagination/offset usage.

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 starts with a specific action and deliverable: 'Return a minimal coherent factual set for a code question' and the full list of content types (symbols, call relationships, conditions, tests, specs, and unknowns). It also distinguishes itself from concept_search by explaining that it uses identifier/graph relevance until embeddings are configured.

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 clearly implies this is for open-ended code questions and for services far as a fallback to concept_search. It does not explicitly identify when to prefer it over search, callers, tests, or other siblings, nor does it name any alternatives besides concept_search. So usage guidance is present but not explicit.

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