get_capability_score

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context by specifying the result is 'static' and includes 'provenance,' implying no dynamic on-chain analysis is performed and that the output is traceable to a source. However, it omits side-effect disclosure, network constraints (Base mainnet vs. testnet), and error behavior for invalid or non-contract addresses.

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 with the primary action front-loaded and zero filler words. The clarifying second sentence 'This is not a safety score' earns its place by reducing the risk of mis-selection against the audit siblings. Every word contributes meaning.

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?

The tool is simple (one required parameter), but with no output schema, the description should clarify what the returned index looks like and what 'provenance' means as a data structure. It provides no error-case context and no indication of the output scale or format, leaving an agent to guess at result interpretation. For a single-parameter tool the gaps are moderate rather than severe.

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%, so the description must compensate for the undocumented 'address' parameter. The phrase 'for a Base contract' adds the crucial semantic that the address must be a contract on Base, not an EOA or a contract on another chain. It stops short of specifying address format, checksum requirements, or whether the contract must be previously indexed or verified.

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 names a specific verb ('Return') and a specific resource ('static capability coverage index and provenance for a Base contract'), so an agent knows what the tool produces. The negative clause 'This is not a safety score' helps differentiate it from the audit-oriented siblings like audit_contract and m2m_audit_contract. However, 'capability coverage index' is never defined, leaving some ambiguity about what exactly is being measured.

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 no explicit guidance on when to use this tool versus any of the eleven siblings. The only directional hint is the negation 'This is not a safety score,' which tells an agent what this tool is not for, but does not say which alternative to pick when a safety score is needed. No conditions, prerequisites, or routing logic are provided.

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