oldweb-network

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

Annotations already declare read-only, idempotent, non-destructive behavior, so safety is covered. The description goes well beyond that: it discloses the comparison semantics (IPv4 and IPv6 compared separately), output shape (normalized subnets, exact overlapCount, up to 200 input-index pairs), truncation metadata (omittedOverlaps/truncated), and a prompt-injection caveat treating returned evidence as untrusted data — genuinely useful behavioral 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?

Front-loaded with the core action, then output guarantees, then the security caveat. Dense but every clause carries information; the only mild cost is the long enumerative middle clause, though it is justifiable given there is no output 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?

With no output schema, the description compensates thoroughly by describing returned fields, truncation metadata, and IPv4/IPv6 separation. Combined with annotations covering safety, an agent has everything needed to call and interpret this tool 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?

One parameter with low declared schema coverage, so the description carries much of the burden: it specifies the accepted format family (IPv4/IPv6) and the cardinality cap of 100, which aligns with the schema's maxItems. It does not add per-item format or error-handling detail beyond the schema's own example.

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 ('Detect') and resource ('overlapping ranges among up to 100 IPv4/IPv6 CIDRs'), with scope limits baked in. An agent can immediately tell this is an overlap-detection tool, distinct from inspect_subnet (single subnet inspection) and plan_subnets (allocation).

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 by the purpose — call it when you need to find overlaps in a set of CIDRs — but there is no explicit when-to-use guidance, no conditions selecting it over inspect_subnet or plan_subnets, and no prerequisites. Minimum viable routing information.

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 the safe-read profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to add the behavioral layers that matter: results are serialized as decimal strings, IPv4 results include mask and usable-host bounds with special /31 and /32 handling, and returned evidence is flagged as untrusted data rather than instructions. That last point is a genuinely useful injection-safety disclosure absent from the annotations, though the exact response shape remains unspecified.

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 what is computed before the format and safety notes. Every sentence carries distinct information — scope, output encoding, IPv4 edge-case behavior, and trust posture — with 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?

With no output schema, the description must carry return-value context, and it does: decimal-string serialization, mask and usable-host bounds for IPv4, and explicit /31 and /32 handling. It stops short of enumerating the actual fields an IPv6 response contains, which is the one remaining gap for a parser 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?

There is a single parameter and the schema already documents it fully (100% coverage) with a concrete IPv4 and IPv6 example. The description adds nothing about the cidr argument itself, so the baseline 3 for schema-driven parameters is correct.

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 ('Calculate IPv4/IPv6 CIDR boundaries and exact address counts') and scopes it to a single CIDR input, which implicitly distinguishes it from check_cidr_overlap and plan_subnets. It never names those siblings, so the differentiation relies on inference rather than explicit contrast.

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 tool for deriving boundary/count facts about one CIDR, but there is no when-to-use statement, no prerequisites, and no mention of when to prefer check_cidr_overlap or plan_subnets instead.

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 the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds real value: deterministic 'largest blocks first' ordering, the exact outputs returned (allocations, exact remaining addresses, explicit insufficient-capacity results), and a prompt-injection warning that returned evidence is untrusted data. It does not contradict any annotation, since allocation planning is a pure read.

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 action and scope, then behavior, then the untrusted-data caveat. No filler or repetition of schema fields.

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 usefully enumerates the return payload (allocations, remaining addresses, insufficient-capacity results), which is what an agent most needs. It is slightly thin on ordering guarantees under conflicting requests and on how partial failures are reported alongside successes.

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 only 50% (the nested label/prefix fields are undocumented in the schema), and the description compensates by explaining that requests are 'labeled prefix requests' and that the parent is an IPv4/IPv6 CIDR block. It still does not clarify that 'prefix' is a prefix length in bits or the meaning of 'label' as an identifier, leaving a small gap.

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 gives a specific verb and resource: 'Allocate up to 100 labeled prefix requests within an IPv4/IPv6 parent.' The scope (up to 100, IPv4/IPv6, parent-contained) is concrete, and 'allocate' is clearly distinguishable from the sibling verbs 'check_cidr_overlap' and 'inspect_subnet'.

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 by the operation itself (planning multi-prefix allocations inside a parent), but the description never states when to prefer this over check_cidr_overlap or inspect_subnet, nor any when-not condition. The agent must infer the routing from the verb alone.

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