Just Publish

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

Annotations already cover readOnly/openWorld status, but the description adds high-value operational context the annotations do not: no build step or config, the token/identity handshake (url + site_id + edit_token returned, token is the only way to edit later), and the whole-site replacement semantics with the deletion warning. The only tension is that 'files you leave out are DELETED' sits awkwardly against destructiveHint=false, so the behavioral picture is rich but not perfectly aligned with the declared hints.

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?

Dense but front-loaded: purpose, trigger phrases, call flow, destructive warning, then alternatives. Every sentence carries information an agent needs, though the description is on the long side and the flow/warning material could be tightened slightly.

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 tool with 4 params, an output schema, and sibling tools, the description covers everything needed to call it correctly: required inputs, the create-vs-update branch, the token retention requirement, the destructive replacement risk, and when to pick a sibling instead. Return values are already handled by the output schema, so nothing material 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, but the description adds meaning the schema only hints at: site_id/edit_token are optional on first call and required on updates, and it explains why edit_token must be retained for future edits. It does not add syntax for the files array beyond what the schema documents.

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?

Opens with a specific verb+resource+outcome ('Put a website live at a public URL') and immediately distinguishes itself from siblings by stating deploy REPLACES the whole site, whereas update_site_file changes one file and get_site_files inspects what is live. An agent can route correctly without opening any 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 when-to-use triggers in user language ('I need a website', 'make this live'), then spells out the first-call flow (omit site_id and edit_token) versus later calls (pass site_id + edit_token), and names both alternatives with the condition that selects them (one/few files -> update_site_file; inspect first -> get_site_files).

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 mark this read-only and non-destructive, yet the description adds real value beyond them: it discloses auth requirements (site_id + edit_token), the optimistic-concurrency contract (pass version back so you don't overwrite a newer change), and the sha256 manifest for change detection.

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?

Four tight sentences, front-loaded with purpose followed by return shape, the paths toggle, and prerequisites. No filler; every sentence carries decision-relevant 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?

For a three-parameter read tool with full schema coverage, an output schema, and read-only annotations, the description plus structured fields leave nothing an agent needs missing: it covers auth, return contents, filtering semantics, and the version handoff.

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 clarifies behavior the schema only states in passing: paths selects contents only while the manifest always lists every file, and edit_token/site_id are mandatory. It adds the semantic link to update_site_file's version 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 ('Read the files of a site you already published') and immediately frames the goal (make a targeted edit instead of rebuilding). It is clearly distinguishable from sibling update_site_file, which is the write counterpart referenced by name.

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 clear when-to-use context (read before editing) and explains the paths-optional behavior versus omitting it. It references update_site_file and the version handoff, but never states explicit exclusions or when another sibling like deploy would be preferred.

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 destructiveHint=false, readOnlyHint=false, openWorldHint=true. The description adds important behavioral context the annotations don't: it's a merge not a replace, describes conflict behavior with expected_version, states auth requirements (edit_token), and adds two sharp limitations (cannot delete files, cannot remove index.html). Only missing details around rate limits or partial failure semantics.

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?

Front-loaded with the core merge semantic, followed by use-case examples, workflow guidance, and exclusions in dense sentences. It's on the wordier end but each sentence earns its place; no obvious 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?

Covers purpose, workflow, conflict handling, auth prerequisites, and hard limitations. With an output schema present, no need to describe return values. Complete for an agent to call it 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 100%, so parameters are fully documented in the schema. The description adds workflow semantics for expected_version (conflict on version mismatch) and reiterates required params, but doesn't add much new about parameter syntax beyond what's 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?

States a specific verb+resource (change files of an already-published site) and precisely distinguishes from sibling deploy by describing the merge semantics. Tells the agent exactly what this does vs. what deploy 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?

Explicitly says when to use it ('Ideal for small edits: fix a typo, swap a stylesheet, add one page'), outlines a best-practice workflow (get_site_files first, edit, then call), and names alternatives in the negative ('Cannot delete files - use deploy to drop a file'). Nothing is left to inference.

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