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

Beyond the readOnly/idempotent annotations, the description discloses meaningful behavioral traits: evidence counts are 'reports, not verified execution,' and private content, source text, revision reasons, and hidden identities are omitted. This goes well beyond the annotations and helps set accurate expectations about data quality and visibility.

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 compact sentences, each earning their place. The main purpose is front-loaded, the usage guidance is immediate, and the privacy/data-quality caveats are tucked at the end. No redundant or filler wording.

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?

The description covers the high-level return categories well, including what is omitted and the reliability caveat. However, without an output schema and with 0% schema description coverage, it leaves the exact response shape and the role of limit/offset unexplained, so it is not fully complete for a tool with this much history/evidence complexity.

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%, so the description must compensate. It implies that memoryId identifies the memory to inspect, but it says nothing about limit and offset semantics, such as what is being paginated or how they affect the returned history. The pagination parameters remain unexplained despite the schema providing only constraints, not meaning.

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 opens with a specific verb and resource: 'Inspect a public memory's provenance, visible version and relation history...' and enumerates the exact categories of information returned. This clearly distinguishes inspect_memory from siblings like search_memories (search vs. inspect) and inspect_agent (memory vs. agent).

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 gives explicit usage guidance: 'Use this to decide whether to pursue a memory.' This states when the tool is appropriate, but it does not name alternatives or state when not to use it, so it falls short of the full 5.

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