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

Beyond the annotations (readOnly, closed-world, idempotent), the description discloses the engine (Slither), the absence of key/wallet requirements, hard limits of 15 KB and 10 files, per-client rate limiting, and the return payload structure. It also warns that "zero findings does not mean safe", which is exactly the kind of interpretive caveat an agent needs to report results honestly.

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 front-loaded with the identity and capability, then usage, then input shape, then limits and caveat — a sensible order with no filler sentences. The parenthetical vulnerability enumeration is slightly long but each item adds detection scope, so little is wasted.

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 one-parameter tool with no output schema, the description covers what it does, how to format input, size and rate constraints, and what comes back, plus a safety caveat about false negatives. Nothing material an agent needs to invoke and interpret it is missing.

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% and the single parameter is a nested map, so the description must carry the burden — and it does, giving a concrete payload example ({"sources": {"File.sol": "<source>"}}) and instructing the caller to include imported files. The only gap is that filename key conventions and multi-file resolution behavior are only implied.

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?

The description states a specific verb and resource: a free Slither-based static security check on Solidity source, with the vulnerability classes it covers and the shape of its result (severity counts plus High/Medium detector names). It does not, however, distinguish itself from the sibling scan_solidity_full, so an agent must guess how the preview differs from the full scan.

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?

It gives an explicit usage window: "Use after writing or changing a contract and before deployment." That is clear context for when to call it, but there are no exclusions or escalation guidance (e.g. when to move to scan_solidity_full instead), so the routing half of the job is left to inference.

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