gc_sessions

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description mentions attribution repair, backfills, and review decisions (which imply mutating or destructive operations) but gives no indication of side effects, prerequisites, or consequences. None of the 12 actions have any behavioral detail.

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 a single dense block that lists action names with no grouping, hierarchy, or prioritization. While technically short, the conciseness here is under-specification — it saves words by omitting essential explanatory content. The information density is low because action names without context communicate almost nothing.

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?

This is a complex multi-action tool (12 distinct operations) with no output schema and no annotations, yet the description provides no per-action detail, return behavior, error conditions, or action-to-parameter mapping. A tool this complex with this many operations needs substantial per-action documentation, and the single paragraph is wholly inadequate for agent usability.

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?

While schema description coverage is 100%, the description doesn't map any parameters to actions or explain their role beyond what the schema says. The connection between parameters like 'review_id', 'note', 'decision' and the 'apply_review_decision' action is only inferable, not stated. The description adds minimal value beyond the schema's one-line parameter descriptions.

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 lists 12 action names without explaining what any of them does. 'Session ingestion ops — scanner status, attribution repair, manual scans, and knowledge backlog control' is too vague to convey the tool's purpose, and the actions like 'review_attributions', 'apply_review_decision', 'work_item_summary' have no explanation. It is essentially a menu of command names that doesn't tell the agent what each does or how they differ.

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?

There is no guidance on when to use this tool versus its siblings (gc_recall, gc_retain, gc_reflect, etc.) or when individual actions are appropriate. The description provides no context about which action to choose for a given task, leaving the agent to guess from bare action names.

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