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

The description does not disclose behavioral traits such as side effects, permissions, reversibility, or what happens on success/failure. The annotations indicate idempotent and non-destructive, but the description does not elaborate on these, leaving the actual behavior of actions like set or cache_clear unclear.

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 appropriately sized: it opens with a clear summary then lists actions in a compact, pipe-separated format. It is front-loaded with the main purpose and does not include unnecessary 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?

Given the tool's apparent complexity (many distinct actions), the description is incomplete. It does not explain what each action does, any side effects, or required parameters for each action. It relies on the help tool for full docs, which is not sufficient for a complete understanding.

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 description adds no meaning to the schema parameters. It lists actions but does not explain the role of 'key', 'force', 'value', or 'remote_type'. The schema provides types and defaults but no descriptions, so the parameter semantics are entirely undocumented.

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's purpose as 'Server config and management' and enumerates specific actions (status, set, cache_clear, etc.), which gives a good high-level understanding. It is distinct enough from sibling tools, though it does not explicitly compare with 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?

The description does not explicitly state when to use this tool versus alternatives. It only suggests using the help tool for full documentation, which is a weak form of guidance. There is no indication of prerequisites or typical use cases for the listed actions.

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?

With no annotations, the description carries the responsibility for disclosing behavior. It mentions the side effect of opening a browser 'when possible', and lists return values (URL, browser launched, status). However, it omits potential failures, permission requirements, or any side effects beyond the browser action.

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 two concise sentences, front-loaded with the primary purpose, and includes all essential behavioral information without superfluous details. It earns its length efficiently.

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?

Given the tool's simplicity and the presence of an output schema (likely documenting the return values), the description covers the core purpose and side effects adequately. It lacks details on error handling or integration with other tools, but for a straightforward config command it is sufficiently complete.

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 only parameter is 'ctx', a standard context object, but the description does not mention or explain it. Schema coverage is 0% as the description adds no parameter-specific meaning. While the ctx parameter is typically auto-injected, the description should at least note its presence or purpose, making this a 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 clearly states the verb 'Get' and the resource 'relay configuration URL', and specifies the browser-opening behavior. It distinguishes itself from the sibling 'config' tool by focusing on the relay URL retrieval and browser action.

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 no guidance on when to use this tool versus alternatives, no preconditions, and no mention of when it should not be used. It simply states what the tool does without contextual advice.

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 readOnlyHint and openWorldHint, but the description adds substantial behavioral context: batch per-domain rate limiting (max 50 URLs), crawl depth and max_pages constraints, stealth anti-bot bypass, persistent browser sessions, refetch behavior, and the ability to click/fill/submit via interact. This goes well beyond the annotations and sets accurate expectations.

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 long but well-structured: opening purpose, actionable examples for each of nine modes, and a key-parameters section. It front-loads the core use case and search distinction. Every sentence earns its place given the tool's complexity; the final pointer to 'help' is a minor but useful note.

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 an 18-parameter, multi-action tool, the description is remarkably complete. It documents every action mode with examples, covers nearly all parameters with defaults and constraints, and notes the existence of an output schema. No critical gaps remain for an agent to select and invoke 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?

The input schema has 0% description coverage, so the description carries the full burden. It compensates with action-specific mappings, defaults (max_urls=5, depth=2, token_budget=10000), constraints (max crawl depth 5, max_pages 100), and concrete examples showing how to pass parameters. Only 'prompt' is not explicitly described, but overall semantics are richly defined.

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 'Read and return full page content from URLs or local files' and enumerates nine specific action modes (extract, batch, crawl, map, convert, extract_structured, agent, interact, diff). It distinguishes itself from the sibling 'search' tool by explicitly saying 'For finding URLs first, use the search tool instead.'

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 explicit when-to-use guidance: 'Use this when you have a specific URL and need its content.' It names the alternative search tool, and each action includes an example with concrete parameter usage. The key parameters section further clarifies which parameters apply to which action.

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 idempotentHint=true, covering safety. Description adds that it returns detailed documentation, but no extra behavioral traits beyond what annotations convey. Consistent but not additive.

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?

Efficient: first sentence states purpose, second lists valid values, then a concise quick guide in bullet-style. No fluff, every sentence 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?

The tool has one parameter; description covers purpose, usage guidelines, valid values, and sibling differentiation. Output schema exists but return values are self-explanatory. Complete for the tool's simplicity.

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% with only type 'string' and a default. Description compensates by explicitly listing valid tool_name values ('search, extract, media, config') and explaining each's usage in the guide, adding meaning beyond 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 clearly states 'Get detailed documentation for any tool,' using a specific verb and resource. It distinguishes from siblings via the quick guide that maps each sibling tool to its purpose.

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?

Explicitly says 'Call this when you need full parameter reference or usage examples.' Provides a quick guide comparing sibling tools, stating when to use each (e.g., 'Need to FIND information? Use search'), giving clear when-to-use and when-not-to-use context.

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?

The description openly discloses that the tool downloads files to local storage (a side effect consistent with readOnlyHint=false), and it explains the reserved 'prompt' parameter is ignored. It also describes the legacy action removal, adding 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?

The description is structured with bullet points and examples, front-loaded with the core purpose. It is somewhat verbose due to the workflow and legacy notes, but every section adds value and aids usage.

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?

The description covers actions, parameters, workflow, and even directs to the help tool for full documentation. Given the output schema exists and the tool is complex, the description is remarkably complete and self-sufficient.

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?

With 0% schema coverage, the description compensates well by explaining url, media_urls, media_type, output_dir, and prompt behavior. It also gives defaults and examples, though it omits 'max_items' and detailed accepted values for 'action'.

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 it discovers and downloads media files, lists specific actions (list, download) with examples, and distinguishes from sibling tools like extract and search by naming the resource type (media) and workflow. The purpose is specific and 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 explicitly explains the typical workflow (list then download), tells when to use which action, and points to the alternative for LLM analysis (imagine-mcp's understand action). It also warns that the legacy 'analyze' action is removed, preventing misuse.

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 provide readOnly, idempotent, and openWorld hints, so the bar for extra behavioral value is high. The description goes beyond them by disclosing cost (~$0.032/query for X), authentication requirements (XAI_API_KEY), latency implications of enrich/refine, and backend-skip behavior for region. This is rich, 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?

The description is long but appropriately so for a tool with eight distinct actions and 23 parameters. It is front-loaded with the critical 'NOT full page content' warning and the extract alternative before diving into action details. Each bullet and parameter earns its place through examples, constraints, or caveats.

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?

Given the tool's complexity, the description is remarkably complete: it covers all actions, key parameters, examples, costs, authentication requirements, latency trade-offs, and fallback behavior. It also points to the help tool for full parameter documentation, which closes any remaining gaps.

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 parameter-documentation burden alone. It explains many parameters including query, library, language, expand, enrich, max_results, time_range, include/exclude_domains, handles, from_date/to_date, video, region, and refine. However, a few schema parameters such as limit, topic, categories, and parallel are not described in either the schema or the description.

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 is for finding information across web, academic, X/Twitter, and library docs, and explicitly says it returns listings, not full content. It names the sibling 'extract' as the alternative for reading full pages, which differentiates it sharply. Each action is given a specific verb and resource.

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 gives explicit guidance: use 'extract' for full content, and explains that X results are not a link list because X blocks direct extraction. It also documents when to use each action with concrete examples, including the caveat that region-unaware backends are skipped.

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