fetch_nodes

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

With no annotations, the description carries the full burden and does unusually well: it discloses that unauthorized ids (pending review, rejected, other team) are returned in `missing` rather than raised as errors, and preempts a retry loop by saying this is the review gate, not a failure. It stops short of describing the returned body structure, batch size limits, or auth requirements beyond entitlement.

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?

Four short sentences, all load-bearing: purpose first, then the retrieve_index dependency, then batching, then the `missing` semantics that prevents a costly retry. No filler and no repetition of the field name.

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?

A one-parameter read tool with no output schema — the description covers sequencing, batching, and the non-error `missing` outcome, which are the parts an agent could otherwise get wrong. Only the shape of the returned 'full bodies' and any per-call size constraint are left unstated, which are minor for this 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?

The single `ids` parameter has 0% schema description coverage, so the description must compensate — and it largely does, clarifying that ids are memory node identifiers sourced from retrieve_index and that the parameter is a batch (all wanted ids in one call). It does not state the id format or any cap on how many ids can be passed.

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 and resource — 'fetch the full bodies of specific memory nodes by id' — and explicitly positions it relative to the sibling retrieve_index. An agent can distinguish this from retrieve_index or retrieve_context without opening 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?

Gives an explicit precondition ('after retrieve_index showed you which ones are worth reading') and an explicit batching rule ('Pass every id you want in ONE call rather than one call per id'). Both the when and the how-not are spelled out, which is exactly the routing information an agent needs.

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