PubSpace

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

Goes well beyond the annotations: it discloses immediate URL breakage, a brief dashboard-only undo window, permanent purge with no restore tool, the return shape { ok, id, deleted }, and the page_not_found failure condition. The annotations only flag destructive/openWorld/non-idempotent; the description supplies the reversibility and blast-radius details that actually drive the decision.

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 short sentences, front-loaded with the effect of the call, then the alternative, then the return/failure contract. Nothing is redundant with the schema or annotations, and every clause 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?

No output schema exists, but the description supplies the return shape and the failure case, and it covers reversibility, permissions-adjacent scoping, and the substitution path. Nothing an agent needs to call this mutation safely 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% and the schema already explains the id format and space scoping, so the baseline is 3. The description still adds meaning by tying the id to a failure mode — the id must be in this space and not already deleted, else page_not_found — which 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 and resource ("Delete a page") and immediately names the observable consequence ("its URL stops working at once"), which disambiguates it from hide-style siblings. An agent can tell it apart from unpublish_page without opening either 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 an explicit precondition ("Only use it when the human asked for deletion") plus the named alternative and the condition that selects it ("to hide a page reversibly, use unpublish_page instead"). Both the when and the when-not are stated.

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, idempotentHint and non-destructive behavior, so the description can focus elsewhere — and it does, disclosing the exact return fields, the scope restriction to the connected maker's space, and the page_not_found error. It stops short of describing response size or latency behavior for large html payloads beyond a general 'can be large' warning.

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 tight sentences, front-loaded with the core action and return shape, then usage routing, then error behavior. Every clause carries actionable information — return fields, the html flag effect, sibling routing, failure mode.

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 no output schema, the description carries the return-value burden and does so by naming the metadata fields and the conditional html field. Combined with sibling routing and the documented error case, nothing an agent needs to invoke this 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 earns an extra point by tying include_html to an observable output difference ('metadata always... plus the stored HTML when include_html is true'), which the schema documents only as a field-level note. It does not add id syntax details beyond what the schema already gives.

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 ('Fetch one page by id') and enumerates exactly what is returned (metadata fields plus optional html), so the agent knows the payload shape before calling. It also names siblings ('update_page', 'list_pages') to separate reading a single page from editing or browsing.

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 guidance: read a page before editing it with update_page, and use list_pages to find ids or browse. It also names the failure case (page_not_found) and its conditions (not in this space, or deleted).

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 and idempotentHint, but the description adds real behavioral detail beyond them: no pagination, newest-first ordering, offline pages included (live: false), deleted pages excluded. That inclusion/exclusion rule is the kind of information an agent cannot get from the annotations or schema.

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 paragraph with no filler: scope and ordering first, then the inline response shape, then read-only confirmation, then usage routing. The embedded schema sketch is compact and earns its space since no output schema exists.

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 one-parameter list tool with no output schema, everything needed is present: the return fields are enumerated inline, paging is ruled out, and inclusion/exclusion of offline and deleted pages is stated. Nothing an agent needs to call this 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 q parameter's case-insensitive title/content search is already documented; the baseline would be 3. The description adds a decision rule (pass q to search rather than scanning the full list) and clarifies that omitting q lists everything, giving it modest added value over 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 and resource (list every page in the maker's space), plus ordering (newest first), paging behavior (none), and even the exact return shape. It is immediately distinguishable from get_page, update_page, and the other siblings.

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 names the when: resolving a page_id before update_page / get_page / unpublish_page / delete_page, and reusing an existing project name. It also gives the alternative path (pass q instead of scanning) and the escalation (use get_page when you need one page's HTML).

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?

Goes well beyond the annotations: default unlisted visibility, search-indexing only if the maker opts in on Pro, link-anyone-can-view semantics, that each call consumes a live-page slot, and the exact failure mode (doc_limit_reached plus an upgrade link to relay to the human). Annotations already state non-idempotent/open-world, and nothing contradicts 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?

Front-loads purpose, then the do-not-use-for-existing-pages rule, then visibility/limits behavior, then the return shape. Density is high but every sentence carries actionable information and nothing is repeated from structured fields verbatim.

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 no output schema, the description supplies the return shape ({ url, id, mode, visibility, dashboardUrl }) and the quota failure mode, which is exactly what an agent needs to handle success and error paths. Nothing material is missing for a 4-param create 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 description coverage is 100% and each parameter already carries its own explanation, including the project rename note and the source_type default. The description adds no parameter-level syntax or constraints beyond what the schema states, so baseline 3 applies.

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 (publish) and resource (a new HTML/Markdown page) and specifies the outcome: a live, shareable URL. It also explicitly contrasts itself with update_page and list_pages, so an agent can pick it out of the sibling set 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?

Explicit routing: "Use this only for a brand-new page; to change a page that already exists, call update_page so its URL stays the same (find the id with list_pages)." That names the alternative, the condition that selects it, and the prerequisite step.

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 non-destructive, idempotent and open-world behavior, but the description adds genuinely new context: what survives the operation (content, id, URL, view count), what viewers see, and the failure mode page_not_found for out-of-space ids. It also compensates for the absence of an output schema by naming the return shape { ok, id, live }.

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-loads the core action and preserved-state guarantee, then layers reversal, sibling routing, idempotency and error behavior in four tight sentences with no filler. Every sentence carries distinct information an agent needs.

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?

Complete for a two-parameter mutation tool: state transition, reversibility, idempotency, sibling alternative, return shape and error case are all covered despite there being no output schema and only a small parameter surface.

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 100%, including the page_id sourcing hint and the restore flag semantics, so the schema already does the explanatory work. The description restates restore: true without adding format or edge-case detail, so the baseline 3 applies.

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 (take offline / restore) and resource (page), and precisely explains the resulting state: URL shows an offline notice while id, URL, content and view count are preserved. It explicitly distinguishes itself from delete_page, so an agent can tell the two apart without opening either 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 an explicit routing rule: 'Prefer this over delete_page when the human wants a page hidden or paused.' It also explains how to reverse the action (restore: true) and states that repeated calls are harmless, covering the main when-to-use and when-to-repeat questions.

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?

Goes well past the destructive/idempotent annotations: it discloses the 7-day restore window, Pro-tier history difference, the draft staging lifecycle (nothing live until the maker presses 'Sync to live'), and the specific page_not_found failure condition. This is exactly the extra context annotations cannot carry.

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 action and the sibling differentiator, then the draft workflow, then the error case. Dense and mostly waste-free, though the nested parentheticals make individual sentences long enough to skim poorly.

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?

No output schema exists, and the description still tells the agent what comes back in the draft path (previewUrl) and the failure mode. For a destructive 6-parameter mutation, nothing needed 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 baseline is 3, but the description adds workflow meaning beyond the schema: draft: true stages rather than publishes and the returned previewUrl must be relayed to the human. It does not add anything for title/project/source_type beyond what the schema already says.

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 ('Replace the content of an existing page in place') and immediately clarifies the key consequence (same URL serves new content). It names the sibling it replaces (publish_page) so an agent can discriminate without opening the 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?

Explicit routing rules: use this instead of publish_page whenever the page already exists, and pass draft: true 'when the human asked to see changes before they go out'. Both the alternative and the selecting condition are spelled out.

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