OneKeyAway: who controls this contract

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

Annotations declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds valuable behavioral context: it is free with a 100 calls/day rate limit, the verdict vocabulary (SINGLE KEY, MULTISIG NO TIMELOCK, TIMELOCKED, UNRESOLVED), and the comprehensive scope of what gets resolved. It does not explain error conditions or what an UNRESOLVED result implies operationally.

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?

The description is front-loaded with the purpose but then becomes a dense run-on enumeration of protocols, roles, chains, and verdicts. The chain list in particular is long and could be deferred or summarized, hurting readability.

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 two-parameter read-only tool with no output schema, the description covers what is resolved, the chain domain, and pricing limits. It is complete enough for an agent to invoke correctly, though it could better explain the verdict semantics or when UNRESOLVED occurs.

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% and both parameters are documented in the schema. The description adds chain IDs alongside names, which is useful but partially overlaps with the schema's example list. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('On-chain control path of an EVM contract or Safe') and enumerates exactly what is resolved (proxy type, admin, owners, roles, verdict). It clearly distinguishes itself from 'watch_contract' by focusing on current ownership/control resolution rather than ongoing monitoring.

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?

Usage context is implied by the description ('control path,' 'verdict'), but there is no explicit when-to-use vs when-not-to-use guidance or mention of the sibling tool 'watch_contract'. An agent must infer that this is for point-in-time control analysis rather than monitoring.

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

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

With no annotations, the description carries the full burden and does so well: it discloses the confirmation-email step, the ~15 minute polling cadence, the free-tier limit, the exact monitored change set, and the consent/privacy constraint. The only minor omission is lifecycle behavior (how to stop or manage an existing watch).

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?

A single dense paragraph, front-loaded with the free-tier scope, followed by trigger conditions, timing, and the consent constraint. Every clause conveys distinct operational information; nothing is redundant with the title or schema.

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 3-parameter, no-output-schema, annotation-free tool, the description covers the behavior an agent needs to invoke it safely (consent, email ownership, limits, timing). What remains thin is the undocumented chain/address parameters and the lack of detail on what the tool returns after registering.

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 only 33% — only 'email' is documented in the schema, and chain/address have no descriptions. The description partially compensates by tightening the email semantics ('user's own email address') and implying the address is a contract under watch, but it says nothing about accepted chain identifiers or address formatting, so the gap is not closed.

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?

Specific verb (watch/alert) plus the exact resource and the exact conditions monitored: implementation, proxy admin, owner, DEFAULT_ADMIN_ROLE holders, Safe signers/threshold/modules/guard, Morpho vault timelock. It is clearly a subscription/monitoring tool, which an agent can distinguish from the sibling control_map (a read of current state) without opening schemas.

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 states real usage constraints: free tier capped at 3 contracts per email, requires the user's own email address, and requires explicit consent. It does not explicitly route the agent between this tool and control_map (e.g. 'use control_map for a one-off snapshot, watch_contract for ongoing monitoring'), so the alternative-selection guidance 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.