Show why each block in a relevance-compaction report was kept, trimmed, or dropped, without re-running it or using the network.
Explain a relevance-compaction report (as produced by compact): why every block was kept, trimmed, or dropped. Never re-runs, never touches the network.
| Name | Required | Description | Default |
|---|---|---|---|
| only | No | ||
| limit | No | ||
| report | Yes | ||
| source_text | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It usefully discloses two non-obvious traits — it never re-runs compaction and never touches the network (pure, side-effect-free, offline) — but says nothing about permissions, error behavior, or cost, so the safety profile is only partially 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?
Two tightly written sentences with the purpose front-loaded and no filler. Every clause earns its place, though the second sentence reads as a behavioral caveat rather than structure.
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 four-parameter tool with a nested required object and no annotations or output schema, the description adequately conveys what the tool returns (per-block keep/trim/drop rationale) but leaves the parameters and any validation/failure behavior unexplained. The core purpose is covered; the callable specifics are not.
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 0% across four parameters (report, only, limit, source_text), so the description must compensate and largely does not. The phrase 'kept, trimmed, or dropped' loosely echoes the keep/trim/drop enum on `only`, but limit, source_text, and the shape of the required nested `report` object are never addressed.
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 specific verb ('explain') and resource (a relevance-compaction report), and ties itself to the sibling tool that produces the report ('as produced by compact'). It distinguishes itself from compact by clarifying it does not re-run, though it does not carve out territory against other read-flavored siblings like inspect or recall.
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 implies usage ('a report ... as produced by compact') but gives no explicit when/when-not or a named alternative to prefer or avoid. The 'Never re-runs' clause hints at the boundary versus compact without stating the selection rule directly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.