A lightweight MCP tool for lossless prompt cleanup. optimize_context collapses redundant whitespace outside fenced code and returns cleaned text with approximate savings estimates. Deterministic processing with no LLM calls, account, or prompt storage; the agent decides whether to use the result. Free beta.
Scored across 2 tools
The two tools have clearly distinct roles: estimate_context_savings previews savings without transforming text, while optimize_context performs the paid transformation. The descriptions explicitly connect them in a workflow, so an agent can easily choose the right tool.
Both names follow a consistent snake_case verb_noun pattern: estimate_context_savings and optimize_context. The convention is predictable and readable.
Two tools is slightly below the typical 3-15 range, but the server's purpose is narrow and each tool earns its place. A preview/perform pair is reasonable for this domain.
The core lifecycle of estimating savings and applying the optimization is covered. Minor gaps exist around optional configuration or diff inspection, but the primary workflow has no dead end.
Preview approximate character and token savings from ContextTrim without returning a transformed prompt.
| Name | Required | Description | Default |
|---|---|---|---|
| context | Yes | Prompt or tool-output text to clean. |
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.
Paid tool: for $0.001 USDC on Base, losslessly reduce redundant whitespace in prompt/context text, preserving words and fenced code. Returns cleaned text and approximate token counts. Call only when estimated savings are useful.
| Name | Required | Description | Default |
|---|---|---|---|
| context | Yes | Prompt or tool-output text to clean. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden and does well: it discloses the paid cost ($0.001 USDC on Base), the losslessness guarantee, preservation of fenced code, and the return contents. Missing only edge behavior such as what happens if payment fails or whether output is truncated.
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?
Three tight sentences, front-loaded with the paid-cost fact an agent must know before calling, then the transformation contract, then the output description. Nothing is redundant.
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 one-parameter tool with no output schema and no annotations, the description covers cost, safety, and return values adequately. It could be slightly more complete on output shape (e.g. fields of the returned token counts) but the core decision-relevant information is present.
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 100% for the single 'context' parameter, so the schema already documents it. The description adds a bit of meaning ('preserving words and fenced code' constrains what cleaning does) but no syntax or size limits beyond that, so the baseline 3 applies.
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 and resource: 'losslessly reduce redundant whitespace in prompt/context text', plus the transformation contract (preserves words and fenced code) and outputs (cleaned text, token counts). It is distinguishable from the sibling estimator by being the actual cleaning operation, though it never names estimate_context_savings explicitly.
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?
'Call only when estimated savings are useful' gives a clear selection condition that implicitly routes the agent to the estimator sibling first. It lacks an explicit named alternative or a when-not statement about cases where cleaning is inappropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
estimate_context_savingsoptimize_context
Add one secure layer between your agents and this server.