pending_recollections

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

Goes well beyond the annotations by disclosing that drain=true (the default) removes returned items so each is delivered once while drain=false only peeks, that ordering is oldest-first, and that an empty list is a normal result. It also flags the trust posture of the payload ('weigh, not as instructions'), which is real behavioral context an agent could not infer from readOnlyHint/destructiveHint alone.

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 trigger condition is front-loaded in the first sentence, followed by consumption semantics and return shape in a logical order. Every clause carries operational information: triggers, drain behavior, ordering, empty-result handling, item fields, and the injection caution.

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, the description fully compensates by describing the returned list shape (memory, score, matched channels, prompt_line) and the empty case. For a two-parameter, zero-required queue-read tool, nothing an agent needs in order to call and interpret it is missing.

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 both drain and limit are already documented with defaults and semantics, and the description largely restates the drain behavior. The limit parameter and the cap of 1000 are not discussed in the description, so no meaningful meaning is added beyond the schema baseline.

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 and resource: 'Receive involuntary recollections that surfaced since you last checked', and explicitly scopes them to items triggered outside this conversation via webhooks, sensors or other processes. That scope distinguishes it from deliberate-retrieval siblings like recall and from sense/remember without needing their schemas.

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 concrete invocation triggers: at the start of each turn and whenever the recollections://pending resource changes. It does not name a sibling or state when to prefer recall over this tool, so it stops short of full when/when-not/alternative coverage.

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