KadiConnect

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

Beyond the annotations (which already declare non-destructive, idempotent, non-read-only), the description discloses genuinely non-obvious behavior: partial-update semantics, the empty-string clearing convention, and that the card is publicly live at the returned publicUrl immediately. That last point is a real side effect an agent needs to know.

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?

Four short sentences, front-loaded with the create/update framing, and each one earns its place: cardinality, partial-update rule, clearing rule, required field, and liveness. No filler or restatement of 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 17-parameter upsert tool with full schema coverage, complete annotations, and an output schema (so return shape need not be explained), the description covers every non-schema-derived gotcha an agent needs before calling: create vs update, partial updates, clearing, required field, and immediate public visibility.

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 the schema already carries the per-field meaning and the baseline would be 3. The description adds value the schema does not: the empty-string clearing rule for optional text fields and the create-time requirement on displayName, which reinforces rather than merely repeats the schema.

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 pair and resource ('Create the business card for this account, or update it') and clarifies cardinality ('Each account has one card'), so the upsert nature is unambiguous. It stops short of differentiating from the read-side sibling get_card, which is what keeps it from 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 context is clear: it explains that only passed fields change on update, that an empty string clears an optional text field, and that displayName is required when creating. What is missing is any routing advice toward alternatives such as get_card for reading the existing card, so there are no explicit exclusions.

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 non-read-only, non-idempotent, non-destructive behavior, and the description usefully adds that the generated link tracks its own views and that multiple links (one per channel) are an intended pattern. It does not mention rate limits or the apiKey/auth requirement, but the tracking trait is real context beyond the annotations.

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: purpose plus labeling example first, return value last. The example is illustrative rather than padding, though the trailing 'Returns the URL to share' is partly redundant given an output schema exists.

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 values need not be spelled out, and the description covers purpose, use case, and the label convention. Remaining gaps are minor: nothing about whether repeated links to the same card are allowed or the auth fallback, which the schema already handles.

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 the baseline applies: all three parameters (name, slug, apiKey) are already documented in the schema, including the labelling intent and the auth fallback. The description adds no syntax, format, or defaulting detail beyond what the schema states.

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 and resource ('Create a labelled link to the card') and adds the distinguishing trait that the link tracks its own views, which separates it from get_shareable_links or create_or_update_card. It stops short of explicitly naming the sibling it is not, so it is clear but not maximally differentiated.

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 only implied through the example of one link per outreach channel ('LinkedIn DMs', 'Conference 2026'); there is no explicit when-to-use statement, no when-not-to-use, and no pointer to alternatives such as get_shareable_links for reading existing links.

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, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile is fully covered. The description adds only the shape of the returned metrics, and since an output schema exists that job is already done, so it contributes little behavioral context beyond the annotations.

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 sentence with no filler, front-loaded with the purpose and followed by the metric list. Every clause 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 an output schema, full annotation coverage, and 100% schema description coverage, the description only needs to establish purpose and scope, which it does. The minor omission is that default scoping (falling back to the caller's own card) is handled by the schema rather than the description, which is acceptable given the surrounding coverage.

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%: both slug (defaults to the authenticated user's own card) and apiKey (only needed without an Authorization header) are fully documented in the schema. The description adds no parameter detail, so this is the baseline case where the schema does all the work.

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 ('View statistics') and resource ('business card'), then enumerates the exact metrics returned (views, saves, saves to contacts, click counts by link type, last-activity timestamps). This is clearly distinguishable from siblings like get_card or get_leads, which would return card content and lead records rather than aggregate metrics.

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 enumerated metrics imply when the tool is useful (when aggregate stats are wanted rather than raw records), but there is no explicit when/when-not statement and no mention of alternatives such as get_leads or get_card. Usage is inferable but not stated outright.

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 establish readOnly, idempotent, non-destructive, closed-world behavior, so the description doesn't need to restate safety. It adds real value by disclosing the empty-state contract (card: null when none exists) and the shape of what is returned, which the annotations do not cover.

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: the retrieval scope is front-loaded and the null-return caveat follows immediately. No filler or restatement of 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 zero-required-parameter read tool with a full output schema and rich annotations, the description is nearly self-sufficient; the return shape is covered by the output schema. Minor gap: it never connects itself to the create_or_update_card sibling that produces the card it reads.

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?

The single apiKey parameter is fully documented in the schema (baseline 3 at 100% coverage), including the note that it's only needed when no Authorization header was configured. The description adds nothing about parameters, which is acceptable given the schema does the work.

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?

Names a specific verb (Retrieve) and resource (the authenticated user's business card), and enumerates the resource's contents (contact details, social links, theme, lead-capture settings) plus its public URL. This makes it clearly distinct from write-oriented siblings such as create_or_update_card.

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 only implied: an agent can infer this is the read path for the card, but the description never says when to prefer it over create_or_update_card or that it needs no inputs. No alternatives or conditions are 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?

Goes well beyond the annotations with the prompt-injection warning about untrusted visitor-typed fields, the privacy constraint on sharing third-party personal data, and the free-plan lock once the card passes 50 views. These are exactly the operational traits an agent cannot infer from readOnlyHint/idempotentHint.

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?

Front-loaded with the verb and resource, then clearly partitioned into SECURITY and PRIVACY blocks. Slightly verbose in restating read-only twice ('Read-only' plus 'cannot create, edit or delete'), but every part carries actionable content.

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 an output schema and full annotations available, the description fills the remaining gaps – when leads exist, untrusted-content handling, privacy limits, and plan-based data locking. Nothing needed to call or safely interpret this tool 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 100%, with limit, offset, apiKey and a status enum all documented inline, so the baseline is 3. The description only echoes the status filter and adds ordering ('newest first'), which is not parameter syntax, so no real lift above baseline.

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 and resource ('List the contact form submissions (leads)') plus scope ('on this account's card'), ordering ('newest first') and filterability. It also distinguishes itself from sibling create_or_update_card by naming the tool that must have been used for leads to exist at all.

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 a clear precondition for use ('Leads only exist if lead capture is on (see create_or_update_card)') and an explicit exclusion ('cannot create, edit or delete leads'). It does not discuss routing against other read siblings (get_card, get_analytics), but for a tool with no true read-alternative the guidance is solid.

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 fully covered. The description adds the newest-first ordering and the fact that only 'tracked' links appear, which is modest extra context but stops short of covering pagination, limits, or auth behavior.

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 front-loaded sentence that names the resource first, then the returned fields, then the ordering. No filler, no redundancy.

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, zero-required-parameter read tool with an output schema, complete annotations, and full schema coverage, the description is nearly sufficient. It could note pagination or empty-result behavior, but nothing critical to a correct call 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 100% and both parameters (slug, apiKey) are documented in the schema, including the default-to-own-card behavior. The description adds no syntax or format detail beyond what the schema already provides, so the baseline of 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?

States a specific verb ('List'), resource ('shareable links'), scope ('the card's tracked'), and even what the result contains (URLs, view counts, newest first). It is clearly distinguishable from the sibling 'create_shareable_link' (a mutation) and 'get_upgrade_link' (a different link type).

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 only implied: an agent can infer you call this to inspect a card's links, but the description never states when to prefer it over 'get_analytics' or how it relates to 'create_shareable_link'. No prerequisites or exclusions are given.

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, and non-destructive, so the safety profile is covered. The description adds useful quota semantics (50 free card views) beyond the annotations, but says nothing about auth requirements, error behavior, or what Pro unlocks relative to free.

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, front-loaded with what is returned, then the usage hint. No 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?

An output schema exists, the single parameter is fully documented, and annotations carry the safety profile. The description supplies the remaining business context (plan tiers, view quota) an agent needs to act on the result.

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?

Only one optional parameter (apiKey), and the schema covers it at 100% with a detailed description about when it is needed. The description adds nothing further, which is the correct baseline for a single-parameter tool.

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+resource ('Check the account plan') plus concrete scope ('free or Pro' and 'how many of the 50 free card views have been used'). This clearly distinguishes it from siblings like get_analytics and get_upgrade_link.

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 a clear usage context ('Worth checking before the user starts a large outreach campaign') that tells the agent when this call is valuable. It does not name alternatives or exclusions, so it stops short of a 5.

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 declare non-readOnly, non-destructive, open-world, non-idempotent. The description usefully adds what the annotations cannot: nothing is charged at generation time, payment happens later in the user's browser, and a user-intent gate applies. It does not warn that repeated calls produce distinct links, which is the one behavioral gap.

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?

Four short sentences, front-loaded with the action and outcome, then the no-charge clarification, then the hand-off instruction, then the precondition. Every sentence carries distinct information.

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-value detail is not needed, and the description covers purpose, safety, and the user-intent gate. The only omission is auth context (the conditional apiKey, already documented in the schema) and duplicate-link behavior.

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%, including the enum values with pricing, so the schema already carries parameter meaning. The description only implies the Pro target and adds no tier-selection or apiKey/authorization context beyond it. 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?

States a specific verb (Generate) plus resource (Paystack checkout link) and the business outcome (upgrading to Pro / unlimited card views). It is clearly distinguishable from siblings like get_subscription or create_shareable_link.

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 an explicit precondition: 'Only call this after the user has said they want to upgrade,' plus downstream guidance to hand the link to the user. It does not name alternative tools or describe what to do if the user is already Pro, so it stops short of full routing guidance.

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 only declare the operation is a non-idempotent, non-destructive write. The description adds critical behavior beyond that: the tool returns an API key, the key is shown only once, the user must store it securely, and the key is later supplied via an Authorization header or apiKey argument. These are non-obvious operational facts an agent cannot infer from annotations.

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 tightly packed sentences: purpose and return value first, then the when/when-not rule, then the operational warning about the key. No sentence is redundant and the most decision-relevant information is front-loaded.

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 three-required-parameter account-creation tool, the description covers purpose, routing logic, and the downstream consequence of the returned credential. An output schema exists, yet the description still flags the one-time key disclosure, which is the detail most likely to cause user harm if missed.

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 name, email, and password are already fully documented in the schema, including the 8-character minimum. The description restates the same three inputs but adds no format, constraint, or edge-case detail beyond the schema, so the 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?

States a specific verb and resource ('Create a new KadiConnect account') and immediately names the key output artifact ('receive an API key (starts with kc_)'). This is clearly distinguishable from all siblings, which operate on cards, links, leads, and analytics rather than account creation.

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 an explicit use condition ('Use this only when the user wants a new account') and an explicit exclusion with the alternative ('if they already have an API key, use that instead'). The agent is told exactly when not to call this tool.

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