Context Pack

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantive behavior beyond that: a per-user external cache, determinism by default, a network/auth dependency (TYPESAFE_API_KEY) for online mode, and the concrete side effects of that mode (relabeling a confidently read intent, demoting files judged irrelevant, reported under modelRead). The 'leaves the target repository unchanged' line overlaps the readOnlyHint but usefully confirms write safety.

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 sentences, front-loaded with the core purpose before the optional online mode, with no filler. The third sentence is dense and somewhat run-on, but every clause carries information about behavior the agent needs.

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 read-only, cache-backed generation tool with no output schema, the description covers what is produced, the default behavior, the opt-in network path and its prerequisites, and a named output field (modelRead). An agent has enough to invoke it correctly without opening the schema, and return-value detail is minimal since the packet structure is described inline.

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 100%, so the baseline is 3. The description's online explanation largely restates the schema's own description of that flag (intent reading, confidence gate, TYPESAFE_API_KEY, offline fallback), adding little beyond the schema, and it says nothing about path, paths, limit, includeEvidence, or includeMarkdown.

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 concrete verb and resource ('Generate a task-aware local context packet') and enumerates the packet's contents (primary files, related files, tests, validation commands), which distinguishes it from simpler retrieval siblings like repo_search or repo_map. It stops short of naming which sibling to prefer when, so it is clear but not fully differentiated.

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?

Gives real usage conditions for the optional mode ('pass online:true to also ask a System One model... needs TYPESAFE_API_KEY') and notes the deterministic default, so the intended workflow is implied. However, it never states when to choose context_pack over alternatives such as review_context, repo_inspect, or change_impact, leaving sibling selection to inference.

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