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

Beyond readOnly/idempotent annotations, the description discloses cache-only behavior, exact content-keying, the missing/unavailable status semantics, return shape, and the api:read requirement. These details materially affect how an agent interprets results and avoids assuming fresh generation.

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 paragraph is dense but well front-loaded: purpose first, cache behavior next, packet input shape, then return semantics. Every sentence contributes useful information for correct invocation.

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?

There is no output schema, but the description explains return values including cached compression fields and missing/unavailable outcomes. Combined with annotations and full parameter guidance, it is complete for an agent to call and interpret the tool.

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%, but the description compensates by documenting the observations packet shape, field meanings, kind enum options, fact_fragments and significance_facts limits, optional observed_at, and return statuses. This adds substantial semantic clarity beyond the raw schema.

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 states a specific verb/resource: cached short wording for Home observations in Gambit. The cache-only constraint and exact-match behavior clearly distinguish it from tools that generate fresh model output, such as ask_gambit_agent. An agent can understand the tool's unique role without opening the 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?

It gives clear context: cache only, never runs a model, never reads the account, and missing means 'no summary yet' with a fallback to use the facts you sent. It does not explicitly name sibling alternatives, but the operational boundaries are well defined.

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