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

With no annotations, the description carries the full burden, and it does disclose the output shape ('Одно фото — файл, несколько — ZIP-архив') plus the pixel ceilings for each level, which is genuine behavioral context. It says nothing about whether the original is left untouched, permission/auth needs, or any rate limits, so the safety profile stays unknown.

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?

Four short lines, each carrying distinct information: formats, output multiplicity, level tiers, and the target_kb override. Nothing is repeated from the name or padded, and the parameter semantics are front-loaded where an agent will read them.

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 3-parameter tool with an output schema (so return values need no explanation), the description covers formats, output shape, tiers, ranges and parameter precedence. The remaining gap is tool-selection context against resize_image/compress_pdf and any note on original-file preservation.

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 0%, yet the description documents all three parameters: file_urls as public URLs, level with its three named tiers, default and resulting pixel dimensions, and target_kb with its 10–50000 range and its precedence over level. This fully compensates for the empty schema, including enum-like values the schema itself lacks.

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?

Specific verb + resource ('Сжимает фото') with an explicit supported-format list (JPG, PNG, WEBP, HEIC), which lets an agent separate it from compress_pdf at a glance. It stops short of naming an alternative (e.g. resize_image) or stating what it does not handle, so sibling differentiation is implicit rather than explicit.

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?

It gives real conditional guidance between parameters — 'target_kb ... тогда level не используется' clarifies that setting a target size overrides the quality level. There is no guidance on when to choose this tool over resize_image or compress_pdf, so tool-selection context is only implied.

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