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

Annotations only declare read-only, non-destructive, open-world; the description goes well beyond them by disclosing that the read recomputes progress with a full corpus query, making it heavier than a cached lookup, and that the numbers stay accurate even when a worker task timed out. That consistency guarantee and compute cost are non-obvious traits an agent cannot get from structured fields.

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?

Front-loads what is returned, then tacks on cost, freshness semantics, and polling role — a sensible order. The worker-timeout anecdote is slightly verbose but earns its place by justifying the freshness claim.

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?

With no output schema, the description carries the return-value burden and does name the three fields the caller should read. It does not enumerate possible 'status' values, which is the one gap for an agent that must branch on build state, but otherwise it is complete for a single-parameter read tool.

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 100% and the single profile_id parameter is already documented as 'id автора из list_authors'. The description adds nothing about the parameter, so the baseline 3 applies; no deficiency, but no added value either.

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?

Names the resource precisely (author corpus build state) and enumerates the returned fields: reels_total, reels_done, status. The verb is implicit ('get/read state') rather than stated, and it does not contrast itself with close siblings like author_stats or author_report_get, so the agent must infer the split.

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?

'Читать бесплатно' establishes that this read costs no credits, a real selection signal against paid analytics siblings. The final sentence explicitly assigns the polling role for author_dossier_build, which is exactly the kind of routing guidance that matters. It gives no when-not or failure-handling guidance beyond that.

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