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

Annotations already declare the safety profile (not read-only, not destructive, not idempotent, closed-world), so the description's burden is lighter. Its only added behavioral signal is "The result says whether the target was met," which usefully warns that compression can miss its goal, but the description never says whether output is a new file or an in-place replacement, nor what happens with conflicting level/target inputs.

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?

Two short sentences, front-loaded with the operation and immediately followed by the parameterization modes. No filler, no restatement of the title.

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 the description need not explain return values or the target-met flag, and it wisely does not. What is missing is the multi-source file input story and the interaction between the two compression modes, which matters for a six-parameter tool with a nested file object.

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?

With 67% schema coverage, the baseline is 3; the schema itself documents file, file_id, file_url, and library_file_id. The description reinforces the level enum and the MB unit for target_size_mb but adds nothing about the three alternative file-input paths (attachment, FynePDF file_id, public URL, library file) or about precedence between level and target_size_mb.

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 ("Make a PDF smaller") and names the two operating modes, so the agent knows immediately what the tool produces. It does not name or contrast with any sibling, though none of the listed siblings (merge, split, ocr, protect) are plausibly confusable with compression.

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 phrase "at a level (low, medium, high) or under a target size in MB" implies the two usage modes, but it never says when to prefer one over the other, whether they can be combined, or what happens if both are supplied. There is no explicit when-to-use or when-not-to-use guidance against alternatives.

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