NudgeLink

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces the safety profile with 'Returns the text only — it is not saved, queued or sent', which is more specific than the annotation about side effects. It also discloses that output is generated in the user's own voice and offer. It doesn't discuss rate limits or length constraints, so not 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?

Two sentences, front-loaded with the action and resource, then the critical non-persistence caveat, then the parameter semantics. No filler and nothing repeated from the title.

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 simple 3-parameter generation tool with no output schema, the description covers purpose, output nature ('text only'), safety behavior and both non-obvious parameters. An agent has everything needed to invoke it correctly.

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, and it does for two of three parameters: it enumerates 'kind' values ('connection_note' or 'first_message') and explains that 'instructions' steers the angle. The 'lead' parameter is left implicit, which is a minor gap given its self-evident meaning.

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 (write/draft) and resource (LinkedIn connection note or first message) plus the target (one of the user's leads). It is easily distinguished from the read-only siblings (get_inbox, list_leads, get_profile) without opening any schema.

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 description establishes when this tool applies (you have a lead and want an outreach draft) and disambiguates the two modes via 'kind'. It doesn't name an alternative tool or state when not to use it, but no sibling competes for this job.

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 read-only, idempotent, closed-world, non-destructive behavior, so safety is covered. The description adds the scoping behavior (user-wide vs. single campaign) but reveals nothing about time windows, freshness, or what a missing/invalid campaign_id does.

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 sentences, both earning their place: the first defines the payload, the second defines the scoping parameter. Front-loaded and waste-free.

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 single-optional-param read tool with full annotation coverage and no output schema, this is adequate. However, with 0% schema coverage on the only parameter and no output schema, a bit more on campaign_id semantics and result scope/aggregation window would be needed for completeness.

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. It explains that campaign_id scopes results to one campaign, which is meaningful, but says nothing about format, that it's optional, or behavior when omitted (though 'pass a campaign id' implies optional).

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 resource (outreach performance for the signed-in user) and enumerates exactly what is returned: invites sent, accepted, messages sent, replies and reply rate. This is specific enough to distinguish from siblings like get_inbox or list_campaigns.

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?

Explains that passing campaign_id scopes to one campaign, implying the default is user-wide aggregation. But it does not state when to use this versus get_inbox or list_campaigns, nor any prerequisites.

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 readOnlyHint, destructiveHint=false, and idempotentHint, so safety is covered. The description adds real value beyond them by specifying newest-first ordering, that each item carries its prospect, and that replying is impossible through this connector, which is useful scoping context.

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 compact sentences with the core content ('most recent inbound replies, newest first') front-loaded and the read-only constraint stated without padding. Nothing 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?

An output schema exists, so return-field detail is not the description's responsibility, and the ordering plus prospect association are well covered. The only real gap is the unaddressed limit parameter, which keeps this short of fully complete.

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?

There is a single parameter (limit) with 0% schema description coverage and a default of 20, yet the description never mentions it, its meaning, or how many replies are returned. The phrase 'most recent' hints at bounded results but does not compensate for the undocumented parameter.

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 concrete resource (the signed-in user's inbound replies), the ordering ('newest first'), and the joined context ('with the prospect each came from'). This is instantly distinguishable from siblings like list_leads or get_campaign_stats, and an agent knows exactly what data comes back.

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 when-to-use statement, but 'Read-only: this connector cannot reply' implicitly routes the agent to draft_message for outbound handling. No guidance is given on when to prefer this over get_profile or the campaign tools, so usage remains inferable rather than stated.

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 readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, fully covering the safety profile. The description adds that the account info is stable, which reinforces idempotence, but does not disclose authentication requirements, rate limits, or what happens if no account is connected. With annotations carrying the burden, a 3 is appropriate.

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 sentences with zero waste. The first sentence front-loads what the tool returns, and the second adds the narrow use case. Every word 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?

Given the presence of an output schema and full annotation coverage, the description need not detail return values. It does, however, explain the meaning of the returned data, which is helpful. The only minor gap is lack of guidance on error or edge cases (e.g., what happens if no account is connected), but that is beyond the scope of typical tool descriptions.

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?

Zero parameters, so there is no parameter semantics to explain. The baseline for 0 params is 4. The description appropriately focuses on what is returned rather than on inputs, which are nonexistent.

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 resource (the NudgeLink account this connection signs in as) and enumerates exactly what it returns (stable id, company name, sign-in email). This clearly distinguishes it from siblings like draft_message, get_inbox, and list_* tools, which operate on messages, campaigns, and leads.

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 description provides clear context for use: 'Used to tell connected accounts apart.' This gives a motivating scenario, but does not explicitly state when-not-to-use or name alternative tools. There are no obvious alternatives among the siblings for this capability, so the absence of exclusions is less critical.

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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds scope ('the signed-in user's' campaigns) and hints at returned content, but reveals little else about behavior. With annotations carrying the burden, this meets the lowered bar without exceeding it.

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 tight sentences, front-loaded with the resource and scope, then the follow-on usage tip. Nothing 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 zero-param read tool with full annotations and an output schema (which carries the return-value detail), the description is nearly complete. It could go one step further by distinguishing this list from list_leads, but nothing required to call it correctly 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?

Zero parameters, so the baseline is 4. The description correctly implies no inputs are needed and instead tells the agent how the output values are used downstream.

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+resource ('NudgeLink campaigns') and enriches it with returned fields ('targeting (job titles, industries, locations) and lead counts'). It's clear what the tool does, though it doesn't explicitly distinguish itself from the sibling list_leads or get_campaign_stats beyond the resource name.

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?

Gives actionable guidance: 'Use a campaign's name or id with the search tools,' pointing to where the output is consumed. It doesn't name the alternatives or state when *not* to use it, so it stops short of full explicit routing.

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 readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful ordering behavior ('newest first') but nothing about auth scope beyond 'signed-in user's', pagination, or truncation at the limit.

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 short sentences, front-loaded with the core action and scope, with no filler. The return-field list is somewhat redundant given an output schema exists, but it costs little.

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 read-only list tool with zero required params and an output schema, the description covers scope, ordering, and filtering adequately. The main gap is the unexplained limit parameter, which the output schema cannot compensate for.

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 carries the full burden. It explains the campaign filter's meaning but says nothing about 'limit' (its default of 25, cap, or effect), leaving half the parameters undocumented in both schema and description.

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 (List) and scoped resource (the signed-in user's prospects) plus default ordering (newest first). It doesn't explicitly distinguish itself from siblings like list_campaigns or get_inbox, but the resource is unambiguous enough that differentiation is inferable.

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 phrase 'Optionally filter by campaign name' implies when the campaign param is useful, but there is no explicit when-to-use guidance, no when-not-to-use, and no routing to alternatives among the sibling tools.

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