retention

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

With only readOnlyHint=false, the description carries most of the burden for a mixed read/write tool, yet it never says whether run_hygiene deletes or rewrites metadata, whether set_layer can move data into an irrecoverable 'frozen' state, or what the request_id/expected_revision concurrency contract implies. The phrase 'tier and semantic closure remain explicit' is unexplained jargon rather than behavioral disclosure.

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?

It is a single short sentence with the operational gist front-loaded, which is good. However, the trailing clause about 'tier and semantic closure' consumes space without conveying actionable meaning, so not every sentence earns its place.

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?

An output schema exists, so return values needn't be explained, but for a three-variant tool that includes mutations, the definition leaves out what hygiene actually does, what a layer change costs, and any safety prerequisites. The complexity of the oneOf schema is not matched by the description's depth.

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 parameter meaning is already carried by the schema (NodeRef, Layer enum, budget_chars, request_id, expected_revision). The description adds nothing beyond the word 'tier', so baseline 3 applies.

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 names three loosely-coupled capabilities — setting a 'recall layer', and inspecting/running 'metadata hygiene' — but the vocabulary ('recall layer', 'tier and semantic closure remain explicit') is idiosyncratic and never grounded in the layer enum or the set_layer/preview_hygiene/run_hygiene actions the schema actually exposes. An agent can guess it's about retention policy, but cannot confidently map the description to what each action does.

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 siblings like forget, lifecycle, pin, or reflect, nor on how to choose among the three actions. 'Inspect' vs 'run' hints that preview_hygiene is the safe read and run_hygiene the mutation, but no exclusion or prerequisite is stated.

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