Hunch

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the description does not need to restate safety. It instead adds genuinely new disclosure: the verdict is deliberately hedged ('never tells you a message is trustworthy and never calls anyone a scammer'), the engine is fixed and server-side, and submitted text is analyzed but not stored. It stops short of noting latency, input-length limits, or what the response object contains, which keeps it below a 5.

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 action is front-loaded and the paragraph flows from input to output to guarantees. The parenthetical about the extension and site is slightly promotional, but it does carry real information about engine consistency rather than being pure filler.

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?

With no output schema, the description does the necessary work of sketching the return shape ('what stands out and the smallest next step') and sets expectations about verdict hedging and data handling. What remains missing is any routing guidance relative to the single sibling tool, which matters for a three-parameter checker sitting next to another verification tool.

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%, so text, sender, and subject are already fully documented including the consequence of omitting sender. The description only reinforces that it reads the words supplied rather than a screenshot, adding little meaning beyond the schema; baseline 3 applies.

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 uses a concrete action ('Paste or forward a suspicious message') and states what comes back ('what stands out and the smallest next step you can take'), so the verb and resource are unambiguous. It lacks any differentiation from the sibling check_official_channel, which is the only thing keeping it off a 5.

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?

The opening sentence clearly establishes the triggering situation: the user has received a suspicious message and wants it assessed. There is no explicit when-not-to-use guidance and no mention of when check_official_channel would be the better choice, so the agent must infer the boundary between the two tools.

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?

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds meaningful behavior beyond that: answers come only from a public-source list drawn from each organization's own pages, with a source link and date, and results are not confirmed by Hunch. It also discloses exactly how misses are labeled ('not listed', never 'unofficial'), which is operationally important.

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?

Three sentences, front-loaded with the core question, followed by the sourcing caveat and the negative-result semantics. Every sentence carries information; the parenthetical about source link and date is dense but earns its place.

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?

With no output schema, the description carries responsibility for framing results, and it does so: it explains the source of truth, the 'not listed' label, and that absence is not evidence of unofficial status. What remains unstated, such as the concrete response shape or whether a source link is returned per channel, is minor for a two-parameter read-only lookup.

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 100%, so both org and channel are already documented, including the omit-to-list behavior for channel. The description adds only a light restatement of the channel types, which the schema also lists. Baseline 3 is appropriate.

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 operation on a specific resource: asking whether a phone number, domain, email, or app is a channel an organization publishes on its own site. It is clearly distinct from a generic lookup. It does not name or differentiate from the sibling check_message, which keeps it short of a 5.

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 is implied through the phrasing 'Ask whether...' and through the explicit interpretation rule (absence is never evidence against a channel), which tells the agent how to use a negative result. There is no explicit when-to-use or when-not-to-use statement and no reference to the sibling tool, so guidance remains implicit.

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