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

With no annotations, the description must carry the behavioral burden. It usefully discloses that results are approximate and that no transformed prompt is returned, implying a safe read-only preview, but it does not explicitly state side-effect freedom, determinism, or what the savings estimate is based on.

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?

A single front-loaded sentence with no filler. Every clause ('Preview approximate...', 'without returning a transformed prompt') contributes meaning.

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 simple one-parameter estimation tool with no output schema, the description covers purpose, approximate nature, and the key return behavior (no transformed prompt). It could be slightly stronger by naming optimize_context as the alternative, but nothing essential to correct invocation is missing.

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%, and the single parameter 'context' is already documented as 'Prompt or tool-output text to clean.' The description adds no parameter-specific guidance beyond the schema, so baseline 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?

States a specific verb ('Preview approximate character and token savings') and resource ('from ContextTrim'), making clear it is an estimation tool rather than a transformer. The phrase 'without returning a transformed prompt' implicitly distinguishes it from optimize_context, though it never names the sibling.

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 (preview/estimate instead of applying a transformation), but does not explicitly say when to choose this over optimize_context or what prerequisites exist. The contrast is inferable but not spelled out.

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