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

Annotations already cover read-only and idempotent behavior, so the bar is lower. The description adds valuable behavioral context: matching logic ('by exact value or name, else by text') and return content (entry plus its defining RFC section). This goes beyond what annotations provide.

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, well-structured sentence that front-loads the core purpose, then lists supported registries, explains query semantics, and states the return value. Every clause earns its place with zero 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 an output schema present and annotations covering safety, the description is largely complete for a lookup tool. Missing edge cases like 'not found' behavior and details on 'text' matching are minor gaps, not blockers. Overall it is adequately comprehensive.

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 does enumerate registries (partially redundant with the enum) and clarifies that query matches exact value/name or text. However, it does not explicitly map the two parameters or address formatting, case sensitivity, or text matching nuances. Adds some but not full 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?

The description clearly states a specific verb ('looks up'), resource ('IANA registry'), and enumerates the registry categories. It is immediately distinguishable from RFC-focused sibling tools like rfc_info and search_rfcs, so an agent can select it without deep schema inspection.

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 context implies usage for IANA lookups versus RFC-related siblings, but there is no explicit when-to-use or when-not-to-use guidance, nor any mention of alternatives. The usage is inferable but not directly 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 carry readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond annotations: the 20-item batch limit, acceptance of varied identifiers (RFC number, BCP, STD, draft name), and the fact that it resolves the full replacement chain to its end. No contradiction with 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?

One dense, front-loaded sentence states the scope and return fields, followed by a single usage directive. Every clause earns its place; there is no filler or repetition of schema 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 structure need not be spelled out, and annotations cover the safety profile. The description explains the input domain, the batch limit, and the resolved output semantics. Minor gap: it does not describe behavior for invalid/unknown identifiers, but this is acceptable given the output schema and annotations already carry significant weight.

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 0% and the schema only says 'array of strings' with maxLength 100. The description fully compensates by specifying exactly what the ids array accepts: RFC numbers (RFC 2616), BCP 14, STD 97, or draft names. This is critical semantic detail the schema does not provide, and it is complete.

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 specific verb ('get') with a clear resource (RFC status/replacements) and enumerates the exact fields returned: title, status, current-ness, obsoletes, replacement chain, updates, and links. It clearly distinguishes from siblings (iana_lookup, rfc_section, search_rfcs) since none of those cover status/replacement-chain resolution.

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?

Provides an explicit trigger: 'Use before citing or implementing an RFC.' This tells the agent when to reach for the tool. However, it does not name sibling tools as alternatives (e.g., 'for a section, use rfc_section') or state when not to use it, leaving the exclusion logic implicit.

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 indicate read-only, idempotent, non-destructive behavior. The description adds meaningful context: verified errata are included, obsolete RFCs trigger a warning, and mode-dependent output is described. It does not cover edge cases like not-found behavior, but this is not a contradiction.

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 primary return value, then mode variants and the warning. 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 and read-only annotations present, the description covers all invocation modes and the obsolete-warning behavior. It is sufficient for an agent to select and call the 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?

Schema coverage is 75%, and the description adds semantics for the undocumented section parameter (number like 15.5.5 or title) and clarifies the find parameter's role. Subtree is only described in the schema, but the description goes beyond schema for the main mode-switching params.

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 clearly states the tool returns exact RFC section text with errata, and describes distinct modes for find and table-of-contents. It is specific about the resource and verb, though it does not explicitly distinguish itself from siblings like search_rfcs.

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?

It provides clear context for when to use each mode: section lookup by number/title, find for phrase search, and neither for TOC. However, it does not mention when to prefer a sibling tool or any 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 establish read-only, idempotent behavior. The description adds valuable context beyond annotations: ranking of current documents above replaced ones and the specific return fields ('number, title, status, year and what obsoletes each'). No contradiction with 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 tightly written sentences deliver the search scope, ranking rule, and return fields with no filler. The most important operational detail (what it searches) 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?

With output schema present and annotations covering safety/idempotence, the description covers search semantics, ranking, and return shape. The main remaining gap is the meaning of include_obsolete, but overall the agent has enough to invoke the tool correctly for typical searches.

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 50%, and the description meaningfully explains the query parameter as topic-word matching against titles, keywords, and abstracts. However, the include_obsolete parameter is not addressed in the description, leaving its semantics only to the field name and 'Default true' schema note.

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 ('Finds') and resource ('RFCs') with clear search scope: topic words in titles, keywords, and abstracts. The ranking behavior and return fields further distinguish it from siblings like rfc_info and rfc_section, making its role unambiguous.

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 implies usage for keyword/topic searching rather than exact-number lookup or section retrieval. However, it never explicitly says when to prefer this tool over siblings or provides exclusions, so the guidance is only implicit.

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