skim402

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

Annotations declare readOnlyHint=true and openWorldHint=true, aligning with the description. Beyond annotations, the description adds valuable context: the per-call cost ($0.015 USDC via x402) and the hard dependency on a wallet configured in the X-Skim-Wallet-Key connector header. It also notes the schema must have top-level type 'object'.

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 core action and the two input modes, then packed with cost/wallet prerequisites. Zero filler words; 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?

Well-covered for a tool with full schema coverage, read-only annotations, and no output schema. The description handles the mutually-exclusive parameters, cost, and auth prerequisite. Missing a note about expected return shape given no output schema, but annotations plus description make it adequately usable.

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%, so the schema documents all 4 parameters. The description adds marginal value by explaining the preset-vs-schema mutual exclusivity and the top-level type 'object' constraint that isn't in the schema. It does not detail the schema format further, but baseline 3 is appropriate given full coverage.

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?

Description uses specific verbs ('read', 'extract structured JSON') plus resource ('web page via Skim'). Clearly distinguishes from siblings (skim_read reads page content; this extracts structured JSON). Lists preset names and schema option explicitly.

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?

Clearly explains the two mutually exclusive input modes (preset vs schema) and how to choose ('Either pick a preset...or supply a JSON Schema'). Notes cost and wallet requirement as prerequisites. Does not explicitly name sibling alternatives for when to use one vs another, so not 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 already declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds value by disclosing rate-limiting, the paid-wallet alternative, and exact pricing ($0.002 on Base via x402), plus what it strips (nav, ads, boilerplate), going 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?

Three sentences, all earning their place: purpose, content types, and pricing/rate-limit notes. No wasted words, well front-loaded with the primary action first. Could trim slightly but it's efficient for an API with billing implications.

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?

Simple one-param tool with full schema coverage and readOnly/openWorld annotations handles most completeness burden. The description adds the non-obvious context (Skim provider, rate limiting, x402 payment mechanism, return format as recognized Markdown) without fluff, making it complete for a simple fetch 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?

Schema coverage is 100% with a single url parameter well documented. The description compensates by clarifying the URL must be public, enhancing what the schema format:uri implies with provider expectations (public fetchable content). With full schema coverage and one simple param, baseline is 3 elevated to 4.

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?

Clear verb+object ('Fetch... return clean, agent-ready Markdown') plus explicit list of content types (articles, docs, blog posts, READMEs, research papers). Describes what gets stripped vs preserved, which differentiates it meaningfully from siblings like skim_extract and skim_signals.

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?

Clearly states what content it's for and highlights the free-tier rate limit plus paid unmetered option via X-Skim-Wallet-Key. Names the service (Skim 402) giving context on cost/limits, though it doesn't explicitly contrast against skim_extract/skim_signals 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?

Annotations already convey readOnlyHint and openWorldHint, covering the basic safety profile. The description adds valuable behavioral context beyond these: it states the cost ($0.005 USDC per call), the mandatory X-Skim-Wallet-Key header, and that results are ordered newest first. It also warns the tool 'does not work without' the wallet key, which is a critical operational constraint. These details go beyond the annotations without contradicting them.

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?

The description is efficient and front-loaded: it opens with the core purpose, then lists feeds (which, while long, is actionable and saves the agent from opening the schema), and finishes with cost and prerequisite details. Each sentence earns its place. It could be slightly more compact, but the information density is high and nothing is fluff.

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 two-parameter fetch tool with a fully described schema and no output schema, the description covers the essential operating context: what it does, what feeds exist, that returns are structured and newest-first, the cost, and the mandatory header. The only gap is that the structure of returned items is not detailed, but since no output schema exists, the agent might benefit from a hint about fields. Still, the description provides enough for a correct call in most scenarios.

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 input schema already provides descriptions for both parameters: 'signal' explains it selects a feed, and 'limit' explains the max items with a default and no upper cap. The description enumerates the feed values again, which is redundant with the enum but does reinforce awareness. There is no additional semantic guidance about parameter formats, limits, or edge cases beyond what the schema states. With 100% schema description coverage, a baseline of 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?

The description states a specific verb ('Fetch'), a resource ('items from one of Skim's curated intelligence feeds'), and enumerates 18 distinct feed names. This precisely defines the tool's function and makes it immediately distinguishable from the siblings (skim_extract, skim_read) which suggest different operations. No ambiguity remains about what this tool does.

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 about prerequisites (wallet header requirement) and costs, which helps an agent decide if the tool is usable in a given environment. However, it does not explicitly mention when to prefer this tool over the sibling tools (skim_extract, skim_read) or state what those alternatives are for. There is no explicit 'use this when you need a feed, use that when you need extraction' guidance, leaving the comparison to the agent's inference.

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