Agent Memory Bridge

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

With no annotations provided, the description carries full disclosure burden. It mentions 'poll for new signals' which hints at temporal/polling behavior (supported by the 'since' parameter), but fails to declare safety properties (read-only vs. destructive), idempotency, rate limits, or error behaviors that would be essential for a bridge/entry retrieval system.

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 single sentence is front-loaded and contains no wasted words; however, given the tool's complexity (9 parameters, dual operation modes, output schema), the extreme brevity constitutes underspecification rather than efficient communication. The sentence earns its place but insufficient sentences are present.

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 tool with 9 parameters, complex filtering capabilities (tags_any, kind, correlation_id), and an output schema, the description is materially incomplete. It fails to explain the 'bridge' concept, parameter interactions, or the structure of returned data, despite having an output schema that reduces the need for return value explanation.

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%, leaving 9 parameters undocumented. The description provides no parameter names, expected formats, or relationships between parameters (e.g., how 'since' enables polling, or what 'namespace' constrains). The vague phrase 'matching entries' loosely implies the 'query' parameter exists but offers no syntax or usage guidance.

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 uses specific verbs ('recall', 'poll') and identifies the resource ('entries', 'signals'), but relies on jargon ('the bridge') without explanation. It implicitly distinguishes from sibling 'store' by focusing on retrieval, though the dual-purpose phrasing ('or') creates slight ambiguity about the primary function.

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 hints at two usage modes—querying existing entries versus polling for new signals—but provides no explicit guidance on when to prefer this over sibling 'store' or other alternatives. No prerequisites, error conditions, or 'when-not-to-use' guidance is provided.

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