Memory: read facts

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

Annotations already declare readOnly/idempotent/non-destructive, so 'Read-only' is partly redundant, but the description adds real value with no output schema present by describing the return shapes (facts with ids and scores, or the four count fields). It doesn't mention rate limits, pagination, or scoring semantics, keeping it short of a 5.

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 tight sentences, front-loaded with what the tool does and its return shapes, then the sibling routing. Nothing is wasted and no sentence merely restates the title.

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 correctly fills the gap by stating return shapes for both actions, and annotations cover the safety profile. Minor gaps remain: the limit default of 10 and any behavior when no facts match are left to the schema and inference.

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 enum already documents that retrieve requires 'query' and stats requires none, so the schema carries the parameter burden. The description's mention of counts versus matching facts implicitly maps to the two actions but adds no syntax or format detail for query/limit, so the baseline 3 holds.

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 (durable key-fact memory) and describes the two result shapes: matching facts with ids/scores, or counts. It cleanly separates itself from navig_memory_update (writes) and navig_recall (conversation history) without the agent needing to open any 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?

Explicitly routes the agent to alternatives: navig_memory_update for create/change/retire, navig_recall for conversation history. That covers the main when-to-use decision, though it doesn't spell out conditions for choosing 'stats' vs 'retrieve' beyond the action enum.

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