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

Annotations already declare readOnly/openWorld/idempotent=false, and the description adds real value on top: nothing is purchased or saved publicly, budget is denominated in USD, and the response includes warnings, cost estimate, individual links and a TCGplayer cartUrl. It also warns that provider access can fail and that bracket analysis is non-certifying. It does not cover rate limits or how idempotent=false actually manifests (varying recommendations).

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?

Purpose is front-loaded in the first clause, then input contract, then output contract, then safety caveats — a sensible order. It is dense and the middle sentences run long, but nearly every clause carries operative information; the one soft line is the closing bracket disclaimer, which still sets expectations.

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 10-param tool with no output schema and low schema coverage, the description does the heavy lifting: it specifies input formats, output shape (cuts/additions, counts, warnings, cost, cartUrl), and non-obvious exclusions. The gaps are the unmentioned tuning parameters (bracket, maxChanges) and no statement of expected latency or provider rate behavior for a tool marked openWorld.

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 30% schema coverage across 10 parameters, the description has to compensate, and it partially does: deck accepts a full quantity-prefixed list or HTTPS Moxfield/Archidekt URL without query params, replaceCard restricts review to one non-protected card, owned is capped at 150 entries/100 copies, and locked/excluded are newline-separated names. It is silent on qaTest, bracket, maxChanges, and budgetUsd's 0–5000 range, leaving half the parameters explained only by schema defaults.

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?

"Repair deck roles and consistency" is a specific verb+resource, and the deckmender/URL input formats make the operation concrete. It does not explicitly distinguish itself from close siblings like reduce_deck_cost, find_replacements, or change_deck_bracket, so an agent must infer the boundary from the "roles and consistency" wording rather than being routed.

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?

There is genuine conditional guidance for a sub-case: if the URL provider access fails, request a plain-text export, and URL imports exclude sideboards and Moxfield companions. However, it never says when to pick this over find_replacements, upgrade_precon, or reduce_deck_cost, which is the more important selection question for an agent facing nine siblings.

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