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

With no annotations, the description must disclose side effects, state changes, or whether this tool returns a recommendation versus actually allocating resources. It only says 'select', leaving the mutation/read-only nature ambiguous, and EVC is not defined.

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 a single compact sentence with no filler, and the main verb/action is front-loaded. It loses a point only because the undefined EVC term and missing parameter references make it dense rather than self-contained.

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?

An output schema exists, so return values are likely covered, but the tool has a required opaque object parameter, no annotations, and no explanation of how EVC relates to task structure or stakes. This is enough to state the tool's purpose but not enough for an agent to invoke it 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 0%, yet the description never mentions task_structure or stakes, the two parameters. It does not explain what EVC means, what shape task_structure should take, or what stakes values are valid, so an agent cannot populate the required input.

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 action - selecting a compute tier and timeout - and a clear resource (compute budget). 'Adaptive compute budgeting' gives the tool an identifiable role among siblings, though it does not explicitly name alternatives or explain the EVC acronym.

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?

No when-to-use or when-not-to-use guidance is provided. The phrase 'Adaptive compute budgeting' implies a use case, but there are no prerequisites, exclusions, or references to sibling tools such as cognitive.execute_task or cognitive.tree_search.

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