IPDetective MCP by usefulapi

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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so the safety profile is covered. The description adds only the negative scope statement (no IP lookup); it says nothing about rate-limit or auth implications of the call itself, nor how limits are expressed.

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, action front-loaded, zero filler. The disambiguating clause follows the core purpose rather than burying it.

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 no-argument read tool with no output schema, the description says what comes back (request and lookup limits plus current usage), which is enough to call it correctly. Return shape details are the only missing piece, and no output schema exists to cover them.

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. There is nothing parameter-related the description could or should explain, and it correctly implies the call is argument-free.

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: 'Read account request and lookup limits and current usage.' The added sentence 'Does not look up an IP address' separates it from the two lookup siblings, though it never names them.

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 pre-flight/quota check before doing lookups, but there is no explicit 'use this when...' framing or reference to ipdetective_lookup_ip / ipdetective_lookup_batch by name.

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?

Substantially exceeds the annotations, which only say read-only/open-world/non-idempotent. The description discloses the metered cost against the IPDetective allowance, the confirm gate, duplicate collapsing before submission, and the absence of retries or background polling — all behavior an agent cannot derive from the structured fields.

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 scoped sentences, front-loaded with the operation, then the cost gate, then the failure-recovery rule. No filler or restated field names.

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?

There is no output schema, so the description is the only place an agent could learn what a batch lookup returns, and it says nothing about response shape or partial-failure handling. Combined with the undocumented include_info flag, the definition is workable but leaves a notable gap for a metered batch call.

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 ips bound (1–100, public) and the confirm gate, but include_info — defaulting to true, a semantically loaded flag — is never mentioned anywhere, leaving one of three parameters opaque.

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 and resource ("Look up 1–100 public IP addresses in one vendor request") with an explicit cardinality bound that implicitly separates it from the single-IP sibling. It never names ipdetective_lookup_ip as the per-IP alternative, so the differentiation is inferred from the bound rather than stated.

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 real precondition (confirm:true required) and an operational rule (check usage before resubmitting after an error), which nudges the agent toward ipdetective_account_usage. It stops short of an explicit use-this-not-that statement against the single-lookup sibling.

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 cover read-only, open-world, non-destructive and non-idempotent behavior, so the description clears a lower bar. It still adds real value beyond them: it discloses quota consumption ('Uses your vendor allowance'), warns that results are a risk signal rather than proof of abuse, and states that no automatic retries occur, which is directly actionable for retry logic.

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 verb, resource and returned data classes. Every sentence carries distinct information: capability, quota, interpretation caveat, retry behavior.

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 and one of two parameters undocumented, the description leaves gaps: it doesn't explain what include_info does, nor what the response shape looks like or what happens on a non-public/invalid address. Adequate but not complete for a lookup tool whose return payload the agent must reason about.

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 clarifies that only PUBLIC addresses are valid for 'ip' (a meaningful constraint not in the schema), but 'include_info' is never named or explained; the word 'optional' only loosely hints that the extra data classes can be toggled.

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 (look up a public IPv4/IPv6 address) and enumerates the data classes returned: bot signal, datacenter, VPN/proxy, ASN, country. The singular 'an IP address' implicitly separates it from ipdetective_lookup_batch, but the contrast is never made explicit.

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?

'Uses your vendor allowance' and 'No automatic retries' give context about cost and failure handling, but there is no explicit when-to-use or when-to-prefer-lookup_batch guidance. The agent must infer single-IP scope from the wording rather than being told.

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