delete_data_points

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

Annotations already declare destructiveHint=true, so the core danger is exposed. The description adds non-annotated behavioral context: a hard batch limit of 10000, a homogeneity constraint (one data type), and an ownership/auth scoping constraint (only data this client wrote). It does not spell out irreversibility or partial-failure behavior, but the added scoping is substantial.

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 definition is a single front-loaded sentence with no redundant wording. Every clause—count limit, single data type, ownership scope—contributes directly to correct invocation.

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 destructive batch-delete tool with annotations and a moderately documented schema, the description covers the essential scope but omits important operational context: whether deletion is permanent, what happens when more than 10000 IDs are supplied, and whether pre-verification is recommended. The annotations cover the destructive nature, but the description could do more to prevent misuse.

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 coverage is moderate (67%) and the schema itself documents dataType, apiVersion, and dataPointIds with patterns and constraints. The description reinforces the maxItems limit (10000) and the single-data-type requirement, but it does not explain how to choose apiVersion or how IDs relate to dataType, so it adds only marginal meaning beyond the schema.

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 states a specific verb (Delete), a specific resource (data points), and precise scope constraints: up to 10000 points, one data type, and only data written by this client. An agent can immediately distinguish this from read or update siblings without inspecting the 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?

The sentence describes capability rather than when to use it. There is no explicit guidance about when to prefer deletion over update/reconciliation, no prerequisites such as confirming with list_data_points first, and no exclusions or warnings about irreversible loss beyond what annotations already say.

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