agent_recall

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so 'Read-only' is redundant. However, with no output schema, the description adds real value by specifying the return shapes ({ ok, data: { key, value } } vs. a key listing with no values), the not-found error path, and the 'Agent memory is empty' state.

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?

Front-loads the core verb and dual mode, then layers usage and return details efficiently. Dense but every clause carries information; only the redundant 'Read-only' line could be trimmed against the annotations.

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 covers what the tool returns and its error/empty states, and it names the siblings to use for credential or overview needs. An agent has everything required to select and call it correctly.

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% and the single `key` parameter is documented there, so the baseline is 3. The description restates that omitting key lists keys without values, adding little beyond the schema's own wording.

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 (read) and resource (encrypted agent memory) and covers both modes: value lookup with a key and key listing without one. It is immediately distinguishable from siblings like agent_remember and agent_forget, and the dual behavior is unambiguous.

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?

Explicitly says when to use it ('start of an agent loop to rehydrate prior context', 'look up a single remembered fact') and routes to alternatives ('prefer get_project_context for a redacted overview of secrets and get_secret for actual credential values'). Both the trigger and the exclusions are stated.

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