surface

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

No annotations are provided, so the description carries the full burden. It usefully discloses the default layers (cold,frozen), the fact that awake won't load them, and the initiative scoping behavior, but it never states the operation is a safe read, nor describes the return shape or any limits. Partial disclosure for a no-annotation tool.

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?

Three front-loaded sentences that lead with the core concept and then cover usage and parameters, with no filler. The em-dash clauses add density but each 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?

With no output schema and no annotations, the description should ideally cover the read-only nature and return shape. It covers purpose, usage, and parameter scoping adequately, but the lack of any statement about what is returned or the safety profile leaves a real gap for a tool with zero structured support.

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 only 50%, and the undocumented 'initiative' parameter is the one the description compensates for by explaining scoping ('scoped to initiative when given'). The layers format is repeated from the schema rather than added to, so net value is moderate — the baseline 3 for half coverage fits.

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 ('surface') and resource ('nodes from specific memory layers'), and explicitly distinguishes itself from the sibling 'awake' by noting it loads layers 'that awake does not load'. An agent can tell it apart from awake and recall without opening either schema.

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?

Gives a clear use condition ('Use when you deliberately need archived/not-surfaced material') and names the contrasting alternative (awake). It lacks an explicit when-not-to-use or a pointer to a more general sibling like recall, but the routing context is strong.

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