get_context

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

With no annotations, the description carries the full burden and does meaningful work: it discloses that proposals are suggestions, legacy records are unreviewed, accepted decisions are constraints subject to freshness, that map.status/diagnostics preserve missing or invalid knowledge, and that impact is capped at three unique files with directory-anchor expansion. Permission/read-only status is not stated, but the semantic and limit disclosures are substantial.

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 core purpose is front-loaded and the sentence count is reasonable for the amount of information conveyed. Some clauses are dense to the point of ambiguity (e.g., the map.status/diagnostics sentence, and referencing "map" before it is introduced), but there is little outright waste.

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?

With no output schema and no annotations, the description must cover the return shape and it does so by enumerating the assembled categories and the freshness/constraint semantics. It is largely sufficient for an agent to call the tool correctly, though the exact result structure and read-only nature remain implicit.

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 dir, task, and files are already documented, including the boosting behavior of files. The description only restates "pass task and optional files" and adds the three-file impact cap, which is behavioral rather than parameter-level meaning. Baseline 3 applies when the schema does the heavy lifting.

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 states a specific verb and resource ("Assemble task context") and enumerates the assembled content — decisions with rationale/approval/owner/sources/freshness, related tests, file impact, map entries. It is clear what the tool does, but it never names or contrasts with siblings like get_impact, get_snapshot, or full_analysis, which overlap heavily with its stated outputs.

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?

"No initialization or map required. Pass task and optional files" gives prerequisites and a calling pattern, which is useful. However, there is no explicit when-to-use versus when-not, and no routing to the many sibling tools that also surface impact or decision context.

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