fgis_start_download

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

The description discloses several behaviors beyond the annotations: no automatic all-Russia/history download, bulk archive files require interactive portal CAPTCHA, TER registry is not TER table content, search enumeration cannot establish exhaustive FSNB coverage (consistent with openWorldHint=true), bounded jobs retain pending tasks, and the return of a job/dataset ID. These are genuinely useful caveats that align with, rather than contradict, the annotations.

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?

The description is a run-on wall of text where semicolons jam unrelated clauses together (e.g., '['all_public'] selects all adapters; include_archive adds archived legal trees; all_periods includes historical split forms'). Only the opening sentence is properly front-loaded; the rest lacks separation between purpose, parameter semantics, and warnings. Information-dense but poorly organized.

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 7-parameter tool with no output schema and 0% schema coverage, the description carries a heavy burden and covers most parameters, the return value, and key caveats. But the disorganized structure and lack of explicit parameter-name mapping mean an agent could misapply the hints, and there is no guidance on behavior when all parameters are left null (0 required). Information is present but hard to reliably extract.

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 0% schema description coverage, the description must compensate, and it substantially does: collections (each scans 01..99), price_books structure [{zone_id,period_id}], sources from fgis_sources, include_archive (archived legal trees), all_periods (historical split forms), and max_tasks (bounds traversal). However, the mapping is loose prose requiring the agent to parse which clause corresponds to which parameter name, so it doesn't fully compensate for the coverage gap.

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 opens with 'Start durable download', a clear verb+resource that identifies the action. It is distinguishable from siblings like fgis_job_status, fgis_cancel_job, and fgis_resume_job which manage jobs rather than initiate downloads. However, the purpose gets buried under a dense stream of parameter hints and warnings, diluting the clarity slightly.

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?

No explicit when-to-use guidance or alternatives are given. The description references fgis_sources ('sources from fgis_sources traverses actual catalogues') but never explains when an agent should start a download vs browse sources first or query an existing dataset. There are no exclusions or conditional routing rules, leaving the agent to infer usage context.

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