call_contract

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

With zero annotations the description carries the full burden, and it does substantial work: it discloses that the tool signs and broadcasts (an irreversible on-chain mutation), that spending is metered against a wallet cap, and that 'gt'/'gte' on the wallet's own STX/sBTC are refused because they set no upper bound. Gaps remain — no mention that the wallet must be unlocked, that gas is consumed on failure, or whether the call returns a txid versus waiting for confirmation.

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 sentence, then the payload formats follow in scannable bullets with a clear progression from args to post conditions to spend limits. The closing 'Tip' promoting `earning_opportunities` is promotional and does not help the caller invoke this tool correctly, which is the main wasted line.

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-parameter mutation tool with no annotations and no output schema, the description covers the hard parts well: argument encoding, post-condition construction, and the spending-cap interaction with postConditionMode. It stops short of stating the preconditions (unlocked wallet, funded balance) and what the call returns, which an agent still has to discover elsewhere.

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%, but the two untyped array parameters (`functionArgs` and especially `postConditions`, whose item schema is empty `{}`) are only usable because the description supplies their full object shapes for STX, FT and NFT conditions and the typed-argument form. This is genuine meaning added beyond the schema, not restatement.

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 — 'Call a function on a Stacks smart contract' — plus the key consequence, 'Signs and broadcasts the transaction.' This distinguishes it implicitly from read-only siblings, but it never names `call_read_only_function` or simple-transfer tools like `transfer_stx`/`transfer_token` as the alternative paths for those cases.

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 real conditional guidance inside the parameter discussion: when to use 'deny' vs 'allow' post-condition mode and when maxStxSpend/maxSbtcSpend apply. However, there is no explicit 'use this when / use X instead' routing against the many sibling tools that also write to chain; an agent must infer that this is the escape hatch for arbitrary contract calls.

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