fetch_media

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

With no annotations, the description carries the full load and does well: it discloses the 50 MB ceiling, the media types excluded, the side effect of writing an archive into the chat folder, and that paths are returned. What is missing is any note on permissions/authorization or what happens when an id is invalid or exceeds the limit.

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 dense sentence that front-loads the verb and constraints with no filler. Every clause (size limit, type exclusions, archive destination, return value) carries information the agent needs.

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 two-parameter tool with no annotations, the description covers limits, exclusions, side effects, and return values, and an output schema exists so return shape need not be spelled out. It still leaves the identifier formats and failure behavior undocumented, which matters for a tool that writes files.

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%, so the description must explain both parameters. It only gestures at 'с указанными id' and 'папку чата', leaving the format of the string 'chat' (username, numeric id, or link?) and whether 'ids' are message ids or media ids entirely unspecified.

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 gives a specific verb and resource ('Скачивает фото и файлы') plus hard constraints (up to 50 MB, no video/audio) and the destination ('в папку чата в архиве'). This clearly separates it from read-only siblings like describe_media or ocr_photos, though it never names fetch_large_file, which is the obvious adjacent tool for the excluded cases.

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 size cap and the video/audio exclusion implicitly tell the agent when this tool does not apply, which is useful routing signal. However, it never explicitly points to an alternative such as fetch_large_file for oversized files or transcribe for audio, so the agent must infer the handoff.

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