batch_read

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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so thoroughly. It reveals the consistent-snapshot semantics, per-operation caps, default event_limit behavior ('omitted, not absent'), per-direction relationship limits, ordered results with item_index, all-or-nothing failure behavior, and the auth boundary between reads and writes.

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 dense but every sentence carries operational information: entry limits, snapshot semantics, per-operation argument reuse, aggregate caps, cursor behavior, failure atomicity, response size, and auth caution. It is front-loaded with the core purpose and uses compact clauses instead of padding.

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 operation that aggregates multiple read variants, the description covers the essential selection criteria, capacity limits, failure semantics, cursor behavior, and authorization nuance. An output schema exists, so return-value details need not be restated. The only minor gap is that the 'catalog' operation is not explicitly named as list_collections, but the reference is recognizable from the schema discriminator.

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, and it meaningfully does. It explains that searches accept full-text, include_context returns full records with one-hop links, traverse reuses the traverse tool's arguments with max_nodes capped at 100, and aggregate reuses the aggregate tool's arguments. It does not walk through every nested field, but the operation-level semantics it adds are substantial for the single 'requests' parameter.

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: 'Read 1–10 mixed searches, contexts, traversals or catalogs in one consistent snapshot.' This clearly distinguishes batch_read from individual read operations and write tools by stating both the batching behavior and the resource types involved.

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 explains when to use this tool rather than single-operation tools: it is for batching 1–10 mixed reads. It also gives important usage constraints like per-operation limits, the total <=100 cap, the 2 MB response limit, and the warning that reads do not authorize writes. It does not explicitly name individual alternatives and say 'use them when…', but the batching intent is clear.

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