GetShardsTool

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

With no annotations, the description is the sole source of behavioral transparency. It implies a read operation ('Gets') but does not disclose whether it requires special permissions, what side effects (if any) occur, the return format, or how it handles errors or missing indices. The description adds minimal behavior beyond a bare read.

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?

At 10 words, the description is compact and front-loaded, with no filler. It is a single sentence that focuses attention on the core action. However, it is so brief that it sacrifices informative value, making it efficient but under-specified.

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 or annotation, and the description does not explain what constitutes 'information about shards' or the shape of the response. Complexity is low, but the absence of any behavioral or return details leaves the agent guessing. For a simple one-param tool, a short description might suffice, but this one is too generic to be fully contextual.

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 for the 'index' parameter is 0%, and the tool description does not explain it beyond the property name. An agent can infer it likely means the index name, but the description gives no details about expected format, whether multiple indices are accepted, or how it relates to shard selection. The parameter name is self-explanatory, but the description adds no compensatory semantics.

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 'Gets information about shards in OpenSearch' essentially restates the tool name with minimal expansion. It does not specify what information about shards is returned (health, stats, allocation, routing), leaving the tool's exact purpose vague. It differentiates from sibling tools by resource type, but not by the specific kind of shard data provided.

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 provides no guidance on when to use this tool instead of ListIndexTool, IndexMappingTool, or SearchIndexTool. No prerequisites, exclusions, or alternative references are given. The agent receives no context about the appropriate use case beyond the tool's name and generic description.

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