chorus.host

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that by specifying the return payload (full docs as Markdown, identical to the skill.md URL) and noting it requires no Cloudflare account for the Workers it describes. It stops short of tier-5 depth only because there is no output schema for it to complement.

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 primary purpose and the when-to-use triggers are front-loaded, and every clause carries information. The middle topic enumeration is long and slightly run-on, but each listed topic genuinely helps an agent decide whether this doc read will answer the question.

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 zero-parameter, read-only documentation fetch with no output schema, the description fully covers what comes back, why to call it, and where to go for setup. Nothing an agent needs to invoke it correctly is missing.

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, which is the baseline-4 case; the description correctly implies no input is needed and instead points to the setup URL for MCP clients. Nothing further is required of it on this dimension.

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 full beacon.host documentation as Markdown') and enumerates what it contains (REST API, CLI, accounts/API keys, claiming sites, password protection, Workers). It also names the sibling it complements ('something publish_site can't do'), so an agent can distinguish it without opening another schema.

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?

Gives explicit triggers ('before building a backend', 'when the user asks about accounts or limits') and an explicit boundary condition relative to an alternative ('when a task needs something publish_site can't do'). This is exactly the when-to-use vs alternative routing an agent needs.

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 cover the safety profile (readOnlyHint, openWorldHint, idempotentHint), so the bar is lower. The description still adds real behavioral context: output is conditional, with the file list, total size, live version and claim link only returned when a claim_token or an owning API key is supplied.

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: the first front-loads what is returned, the second front-loads the usage scenarios. No filler, no 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?

An output schema exists, so return values need not be spelled out, yet the description still summarizes them usefully. For a two-parameter read tool, everything an agent needs to call it correctly is present.

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 baseline is 3, but the description adds meaning beyond the schema by explaining that an API key that owns the site can substitute for the claim_token — an authorization nuance the schema does not state.

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 (check) and resource (a beacon.host site) and enumerates exactly what is inspected: live status, URL, password protection, expiry. This clearly separates it from publish_site (write) and get_docs (documentation).

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?

Gives three concrete use cases: confirming a publish worked, checking anonymous-site expiry, and inspecting what is published at a slug. It does not name a sibling alternative or state when not to use it, but the context is unambiguous.

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 only declare the safety profile (readOnly=false, openWorld=true, idempotent=false, destructive=false). The description goes well beyond: per-call size limits (4 MB / 10 MB with key, 1000 files), 24-hour anonymous lifetime, versioning with rollback, that each call makes a new version with exactly the files sent, and the password/expiry behaviors.

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 densely packed and front-loaded with the core action, target URL pattern, and key invariants before branching into limits and return fields. No sentence is filler, though the volume is near the upper bound of what stays scannable.

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, yet the description still orients the agent on the claim flow (give claim_url, save claim_token) and update semantics without redundantly restating every return field. For a publish tool with nested file objects and anonymous-vs-claimed behavior, nothing an agent needs to call it correctly is missing.

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 baseline is 3. The description still adds operational meaning: index.html is served at the root, text vs base64-with-encoding='base64' usage, the update-via-slug+claim_token workflow, and what password/expires_at accomplish. It stops short of documenting syntax details like the slug character rules already in 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 names a specific verb+resource ('Publish a website or any file... to a live public HTTPS URL') and states the output location pattern (<slug>.beacon.host) in the first sentence. It is clearly distinguishable from the read-only siblings get_site and get_docs, which retrieve rather than publish.

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 gives a broad, explicit set of triggers ('when the user asks to publish, host, deploy or share a page... wants a temporary preview link... wants a link to something you made') plus the update path ('call again with the same slug and its claim_token'). What is missing is an explicit when-not-to-use or a named alternative among siblings, so it falls short of the 5 bar.

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