get_concepts

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

The description adds significant behavioral detail beyond the readOnlyHint annotation: it explains partial failure handling (missing rows return {ok:false, error, ...repairFields} without aborting the batch), guarantees successful rows always return permanent uid and current canonical slug, and states ordering matches input. It also clarifies that graph relations remain slug-based. This thoroughly discloses error behavior and output guarantees, exceeding annotation coverage.

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 four sentences, front-loaded with the main purpose, then error handling, and a note about graph operations. It is dense with useful information but could be slightly more concise; each sentence adds value, and the structure is logical.

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 a batch-fetch tool with partial failures, the description covers all essential aspects: selector choice, per-row shape, ordering, error behavior, and graph-operation implications. It also references get_concept for output consistency. The batch limits and body effect are in the schema, so the description is complete enough for an agent to invoke correctly.

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 100%, so the schema already documents all parameters including the mutual exclusivity of slugs and uids ('never together') and the batch limits. The description reinforces 'exactly one selector array' and 'immutable uids' but adds no new parameter-specific meaning beyond what the schema provides. With full schema coverage, the baseline of 3 is appropriate.

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 clearly states the tool fetches multiple nodes by exactly one selector array (slugs or uids), with a specific verb ('Fetch') and resource ('nodes'). It distinguishes from the sibling get_concept by noting 'Same per-row shape as get_concept', implying a batch vs single-node usage. The purpose is unambiguous and differentiates well.

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 implies usage for fetching multiple nodes at once, contrasting with get_concept for single nodes, and explicitly notes 'exactly one selector array' to avoid mixing slugs and uids. It also explains the order matches the input array and that graph operations remain slug-based, giving context for when to use this tool. However, it doesn't explicitly state 'use get_concept for a single node' or enumerate alternatives, leaving some inference to the agent.

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