get_task_pack

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

This is a sophisticated tool with meaningful behavioral nuance: default parameters (include_always=True, focus=True), dropping of overflow subtopics into a `dropped` field for on-demand pull, and the specific bypass rule for subtopic-level refs. The description transparently documents all this behavior beyond what the schema annotations (none provided) could convey. No annotation contradictions.

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 dense but well-structured: a one-line purpose, then three paragraphs covering returns, focus behavior, and bypass rules. It's front-loaded with the core purpose in the first line, and the paragraphs build logically. Slightly longer than necessary but every sentence contributes meaningful behavioral detail.

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 5-parameter tool with 100% schema coverage and an output schema, the description is remarkably complete. It explains the return structure (meta+subtopics, linked refs, governance), the focus/dropping mechanism, the always_include merge, and the bypass rule — covering all the non-obvious behaviors an agent would need to correctly invoke and interpret results.

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 the baseline is 3. The description adds meaning above this: it connects include_always to config.json's always_include, explains that focus=True triggers FTS-narrowing and that per_entity_top_k controls max subtopics per narrowed entity, and explains dropped refs relate to per_entity_top_k overflow. This adds semantic context beyond the schema's terse parameter descriptions, though min_score (bm25 relevance floor) is only partly elaborated.

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 opens with a specific verb+resource ('Assemble the full context pack for a task') and then details exactly what it returns (task meta+subtopics, resolved linked refs, deduplicated governance). This clearly distinguishes it from siblings like get_context or get_config, establishing a distinct retrieval role.

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 explains when focus mode is used ('entity-level refs with more than per_entity_top_k subtopics are FTS-narrowed') and when subtopic-level refs bypass narrowing. It explains what focus does (narrowing vs returning dropped refs). However, it doesn't explicitly say 'use X instead when...' to name alternatives among the 33 siblings, though the dropped-refs path mentions get_subtopic/get_context as follow-up tools.

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