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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent operation; the description adds important context beyond that, notably the deterministic VB1 guarantee (identical bytes always produce the identical brain_id) and that include_document=true returns the full graph. It does not discuss cost, size limits, or whether repeated builds create new records, and the deterministic-output claim sits in mild tension with idempotentHint=false, though not as a direct contradiction.

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?

It is dense and front-loaded, leading with the core action, then parameters, then return values and the determinism guarantee. No sentence is wasted, though the mixed clause structure in the format enumeration is slightly harder to scan than a list would be.

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 an output schema present, the description need not enumerate return values, yet it helpfully previews brain_id, content_hash, counts, firing report, and provenance. Combined with the format enum and determinism guarantee, it is close to complete; the missing request_id semantics and any when-to-use guidance are the remaining gaps.

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 does the heavy lifting: it explains that content is the file as a string, enumerates the format values (verdigraph_genome, claude_project_export, openai_assistant, prompt_list, auto), and explains include_document. request_id is not mentioned at all, leaving one parameter undocumented.

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: compiling an agent file into a deterministic, content-addressed brain, with the accepted input formats listed. It is functionally distinct from the siblings (describe_agent, detect_format, verify_brain), but it never names or contrasts them explicitly.

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?

Usage is only implied by the purpose: you build a brain from a file. There is no explicit guidance on when to prefer build_brain over detect_format first, or over verify_brain for an existing brain, and no stated prerequisites or exclusions.

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