chrysalis

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals batching (meta.batch), verbosity levels, and an advisory memory hint, but says nothing about whether dispatched domains mutate data, whether operations are reversible, what permissions are required, or what the return shape looks like. For a multi-domain dispatcher, this leaves the agent unable to judge safety.

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 description is short and front-loads the call signature, which is good. However, the telegraphic notation such as 'Advisory memory.recall: rec:facts_exceed_ctx=true' is cryptic, and the following 'In words' sentence largely repeats that advisory rather than adding information.

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 an 8-parameter dispatcher with no annotations, no output schema, and 0% schema description coverage, the description is too thin. It defers the actual contract to a meta/schema call, omits several parameters entirely, and gives no behavioral details, so an agent cannot invoke this correctly without making additional discovery calls.

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% across 8 parameters, so the description must compensate. It partially explains domain/action via the meta/schema and meta/discover examples and lists verbosity enum values, but agent_id, store_as, telemetry, and session_id are completely undocumented, and the 'params' object semantics remain vague.

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 identifies the tool as a 'Single dispatcher' and gives its call signature, which clarifies its structural role, but it never states what the underlying domains do or what resource the tool actuates. The instruction to call meta/schema for 'the full contract' makes the purpose self-referential rather than self-contained.

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 explicitly says to call domain='meta', action='schema' for the contract and action='discover' for a map, which is useful onboarding guidance. It also gives a rough usage condition ('worth using when the facts do not fit in your context window'), but never states when not to use it or what alternatives exist, leaving the agent to infer the dispatcher's role.

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