dosare_attach

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

Annotations already cover safety (readOnlyHint=false, destructiveHint=false, idempotentHint=true), yet the description adds real behavior beyond them: attaching a declaration cascades its archived recipisas, and attaching a request brings its answer along. That cascade side effect is precisely the kind of context annotations cannot express. It omits what detaching does to those carried-over artifacts.

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?

Two short sentences, front-loaded with the verb and target entities, followed by the cascade behavior. No filler or restatement of the title.

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 6-parameter mutation with no output schema, the description covers the core linking semantics but leaves gaps: no mention of the identifier exclusivity rule, no note on the companyId override interaction, and no indication of the success response or failure modes.

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?

At 50% schema coverage, three UUID parameters (declarationId, requestId, documentId) have no schema description, and the description only loosely hints at their meaning through the entity list. It never states the likely rule that exactly one of the three identifiers should be supplied alongside the required dosar id, which is the key invocation constraint.

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 a specific verb (attach/detach) and the exact resource classes it operates on (declaration, SPV request, ANAF message) linked to a dosar, which is concrete and non-tautological. It does not explicitly contrast itself with adjacent dosare_* tools such as dosare_document or dosare_files_upload, so sibling differentiation is left to inference.

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 implied by the entities named, and the detach flag's effect is stated ('remove the link instead'). However there is no explicit guidance on when to use this versus dosare_document / dosare_files_upload, nor on whether the linking parameters are mutually exclusive.

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