calculate_1040_return

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

With no annotations, the description must carry the behavioral burden. It does disclose that the engine is deterministic and that it returns warnings and open questions (hinting at how incomplete data is handled), which is valuable. It does not say whether running it persists or mutates anything, whether it is idempotent, or what happens on failure — gaps that matter for an unannotated tool.

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?

Three short sentences, each earning its place: action first, then the full return payload, then the exclusivity claim. Front-loaded and free of filler; only minor cost is that the payoff sentence comes last.

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?

An output schema exists, so the description need not enumerate return fields, and it correctly stops at a summary of what comes back. However, for a compute tool with an unannotated mutation-ambiguous surface and an undocumented tax_year parameter, it omits prerequisites and re-run/state behavior, leaving real 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?

There is one parameter, tax_year, with a default of 2026 and 0% schema description coverage, so the description is the only place meaning could be added — and it says nothing about the year, its accepted range, or what the default implies. The parameter is effectively 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?

"Run the deterministic engine" is a specific action paired with a concrete output (every Form 1040 line, schedules, warnings, Markdown audit table). The closing claim "This is the ONLY source of tax numbers" implicitly separates it from the upsert_* input tools and get_return_status, so an agent can tell what role this plays, though the resource is named only implicitly via the tool name rather than in the text.

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 line "This is the ONLY source of tax numbers" gives useful routing guidance away from any tool that might surface numbers, but there is no explicit when-to-use statement, no prerequisite (e.g. inputs must be upserted first), and no when-not-to-use condition. Usage is implied rather than stated.

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