HTML.now MCP Server

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

Annotations only declare the generic profile (not read-only, open-world, not idempotent, not destructive); the description adds non-obvious operational constraints — source must be publicly reachable, private-network targets and embedded credentials are rejected, and completion can be awaited or deferred. It still omits cost/quota implications (implied by the get_api_usage sibling) and doesn't warn that repeated calls re-run the conversion since idempotentHint=false.

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 dense sentence with zero filler; the action sequence and the access constraint are front-loaded. It reads as a run-on with three chained clauses, which slightly hurts scannability, but nothing is redundant.

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 is present so return values need no explanation, but this is a 9-parameter, open-world network tool with zero schema descriptions, and the description accounts for only 2-3 of those parameters and no failure modes (timeouts, blocked URLs, invalid slug). That is not enough for an agent to invoke it confidently.

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% across 9 parameters, so the description carries the whole burden and mostly fails: converter 'slug' and the wait/polling switch get light treatment, while width, height, quality, background_color, strip_metadata, and timeout_seconds are never mentioned at all, leaving no hint that the geometry/quality parameters only matter for image-producing converters.

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 concrete pipeline: fetch a public HTML/supported document URL, submit it to HTML.now with a converter slug, optionally wait for the result. This is far more than the name (convert_image_url) or title (HTML document conversion) convey on their own, and the two structured labels conflict, so the description does real disambiguating work — but it never says what the output artifact actually is (rendered image? PDF?) beyond the vague 'convert'.

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 context is only implied: 'optionally wait for the result' hints that wait_for_completion=false hands off to the sibling get_conversion_status, but that tool is never named. No guidance on when to pick this over a different converter, nor when to call list_converters first to obtain a slug, and no exclusion beyond the private-network/credential rejection.

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, so safety is covered. The description adds the caller-scoped nature (no ability to inspect another account's usage) and names the returned fields, but says nothing about data freshness or consumption of a live quota. A modest addition beyond 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 sentence, front-loaded with the verb and immediately followed by the scope qualifier and the returned data. No filler or repetition of the title.

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 documenting return values, empty parameters, and read-only annotations, the description only has to convey purpose and scope — which it does. Data freshness or quota-refresh timing would be the one remaining nicety for an agent polling usage.

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 tool takes zero parameters, so the baseline is 4 and there is nothing for the description to clarify. The mention of 'caller's' correctly signals that the account is derived from auth rather than a parameter.

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 ('Return the caller's HTML.now API credits, usage, and rate limit') and enumerates exactly which data points come back. None of the siblings (convert_image_url, get_conversion_status, list_converters) overlap with usage/billing reporting, so the distinction is 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 caller's' implies the tool is self-scoped and needs no account identifier, which is useful implied guidance. However, there is no explicit statement of when to reach for this versus other tools, nor any mention of prerequisites or rate limits on the query itself.

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, so safety is covered. The description adds the useful fact that completed jobs return an absolute, temporary download URL, but says nothing about in-progress/failed states, polling cadence, or behavior for invalid job IDs.

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 tight sentences with the core purpose front-loaded and no filler. Slightly thin rather than bloated — the brevity is efficient but leaves gaps handled in other dimensions.

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 values needn't be explained, and annotations cover the read-only profile. However, for a single-param polling tool the description should still indicate how job_id is obtained and what an incomplete job looks like.

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% and the single parameter job_id is never mentioned in the description. The agent gets no hint about where the job_id comes from (presumably the convert call), which is the one semantic detail that would help.

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+resource: 'Check a HTML.now conversion job.' An agent can distinguish it from convert_image_url (which presumably starts a conversion) and the listing/usage siblings, though it never explicitly names the relationship.

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 — this is clearly a polling/status-check tool for a job — but there is no explicit statement of when to call it, what to do while the job is incomplete, or how it relates to convert_image_url.

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=false, so the safety profile is covered. The word 'live' usefully signals the catalog is dynamic, but the description says nothing about result volume, truncation, ordering, or what happens when limit is exceeded.

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 front-loaded sentence with zero filler; the return type and examples earn their 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 output schema relieves the description of explaining return values, so the remaining gap is parameter and workflow guidance. For a discovery tool that feeds a conversion pipeline, an agent still lacks instructions on filtering, paging, and how the slugs connect to the sibling convert tools.

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 carry the parameter burden and does not. It gestures at the search concept but never explains matching behavior, nor does it mention the limit parameter, its default of 50, or its 1-100 range.

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?

Names a specific verb (search) and resource (live HTML.now converter catalog) and states what is returned (valid converter slugs), with concrete examples. It distinguishes itself from siblings like convert_image_url by being a discovery/lookup tool, though it never names them 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?

Usage is only implied: an agent can infer this is the discovery step that yields slugs for later conversion calls. There is no explicit when-to-use statement, no mention of the sibling tools, and no guidance on when to filter with search versus listing everything.

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