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

No annotations are supplied, so the description carries the full burden, and it does disclose one genuinely useful trait: 'Pure: no disk, no network,' which tells the agent there are no side effects or external calls. However, it says nothing about cost/billing implications (the 'sku' parameter and 'quote on input bytes' hint at metering), what happens on oversized input, or what the result looks like, leaving substantial behavioral unknowns.

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?

It is a single dense sentence with no filler, and the core operation is front-loaded ahead of the implementation detail. The parenthetical pipeline listing is compact enough to earn its place, though the trailing 'quote on input bytes' phrase is cryptic in this position.

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?

With eight parameters, zero schema descriptions, no annotations, and no output schema, the description is far too thin for the tool's complexity. An agent can guess the general intent but cannot confidently populate the schema or predict the response, so the definition is not complete enough for reliable invocation.

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% across eight parameters, yet the description barely compensates: 'rerank' and 'reranker' can be loosely inferred from the pipeline description, and 'quote on input bytes' faintly gestures at used_bytes, but 'sku', 'query', 'maxTokens', 'targetRatio', and 'rerankTopK' are never explained. The most important control parameters are left for the agent to guess.

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 names a specific verb and resource ('Compress LLM context extractively') and characterizes the internal method (BM25-lite filter, cross-encoder rerank, dedup). It is distinguishable in broad terms, but it never contrasts itself with the nearby sibling spl_compress, which an agent will also see in the list, so the boundary between the two is left ambiguous.

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?

There is no when-to-use guidance at all: nothing says when this should be chosen over spl_compress, spl_decompress, or spl_agentic_plan/run, nor are prerequisites or typical calling contexts described. The agent must infer invocation conditions entirely from the name and pipeline jargon.

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