sqo_compress_prompt

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

With no annotations, the description must carry the full behavioral burden, and it does disclose two real traits: deterministic output with a stated 55%-85% reduction range, and an active scrubbing side effect on secrets. It leaves open important questions a caller would have, such as whether compression is lossy, whether the original text is preserved, and whether scrubbing is reported back to the caller.

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?

One front-loaded sentence with the verb, the accepted input classes, the quantified benefit, and the side effect. Nothing is redundant and nothing could be cut without losing information.

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 single-input utility this is close to sufficient, but with no output schema the description never indicates what comes back - the compressed string alone, or also a ratio/scrub report. That is the main thing an agent needs to plan the follow-up call.

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?

There is a single parameter whose schema description ('Raw prompt, JSON dump, or log text to compress and scrub.') already covers 100% of the surface, so the baseline is 3. The prose adds no syntax, size, or format guidance beyond what the schema states.

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 plus resource ('compress verbose raw text, repetitive JSON arrays, and noisy log pastes') and adds a second function, secret scrubbing. It is not tautological and is clearly distinct from siblings like sqo_context_pack or sqo_prompt_xray, though it never points to or away from any alternative by name.

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 input classes listed (verbose prompts, repetitive JSON arrays, noisy logs) implicitly tell an agent when this tool fits, which is more than nothing. But there is no explicit when-not guidance, no mention of size limits, and no routing to alternatives for cases where compression is inappropriate.

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