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

Annotations already declare destructiveHint=true and readOnlyHint=false; the description confirms this by saying the page description may be 'replace[d]'. It adds meaningful context beyond annotations: the operation is snapshot-versioned ('using its latest Page Snapshot'), batch-validated, and returns snapshots/receipts that should be reused rather than verified via read/list — a workflow contract the annotations cannot express.

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 sentences, each earning its place: core purpose, batching rule, and post-apply workflow. The main function is front-loaded in sentence one, and there is zero filler or repetition of schema content.

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 moderately complex batch-write tool, the combination is complete: a rich 100%-coverage schema documents every parameter, annotations cover the safety profile, an output schema exists, and the description supplies the missing operational nuance (snapshot provenance, no-verify rule, grouping). The only small gap is that the description never explains where the initial Page Snapshot comes from, though the schema's if_version description partially covers this.

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%, so the schema fully documents operations, path, if_version, facts, basis, content, and description. The description adds only marginal value by linking 'latest Page Snapshot' to the if_version parameter and reinforcing the batching semantics of operations. At 100% coverage the baseline of 3 is appropriate.

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 states a specific verb+resource: 'Add independent Facts' to a page, with a secondary behavior of optionally replacing the page description. This clearly separates it from read/list in intent. However, it does not explicitly distinguish itself from the closely related mutation siblings create and update — the differentiation is implied by the word 'Add' rather than stated.

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 operational guidance: 'Group Facts for one page in one operation' (batching instruction) and 'do not verify with read or list' (an explicit when-not for named alternatives). But it lacks selection criteria for the primary choice among mutation siblings — an agent is not told when to choose add over create or update for adding facts vs. modifying existing content.

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 are mostly negative flags and provide little behavioral context. The description adds meaningful behavior: full-batch validation, applied-mode side effects, and a prohibition on verification reads. It does not describe failure or partial-failure behavior, but the added context is valuable.

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 sentences with no filler. The first scopes the action, and the second provides the most important post-call behavior and an explicit exclusion of read/list verification.

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 a rich input schema and an output schema available, the description covers the key operational context: batch validation, snapshot/receipt reuse, and not re-reading to verify. Minor gaps are the undefined 'dynamic pages' term and lack of failure behavior, but they do not block correct invocation.

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, operations, is fully documented in the schema including CreateOperation fields, constraints, and repeated-path rejection. The description adds no parameter-level 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 and resource: 'Create new dynamic pages after full-batch validation.' The batch behavior is clear, but 'dynamic pages' is not defined and the sibling 'add' is not explicitly differentiated, so it does not earn a 5.

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 post-call guidance: reuse returned Page Snapshots and receipts, and do not call read or list solely to verify success. This is strong when-not/alternative guidance, though it does not clarify when create should be chosen over the sibling add.

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 the tool as destructive, but the description adds substantial behavioral context: the authorization prerequisite, the two distinct delete targets, and the unusual post-apply instruction to reuse surviving Page Snapshots and receipts rather than re-verifying. This goes well beyond the structured annotation 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?

The description is two tight sentences with no filler. The core action and authorization gate are front-loaded, and the post-apply guidance about reuse and non-verification earns its place by conveying critical workflow details.

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 destructive write operation with a detailed schema, annotations, and output schema, the description supplies the necessary prerequisites, acceptable targets, and post-apply behavior. Nothing essential for correct invocation 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 description coverage is 100%, with rich per-property explanations for path, if_version, target, authorization, and FactSelector. The description adds only high-level context such as optional page description and exact facts, which is useful but not necessary since the schema already documents all parameters thoroughly.

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 opens with a precise verb and resources: 'Delete exact Facts with an optional page description, or delete dynamic pages.' This clearly distinguishes the tool from siblings like read, list, move, and update, and leaves no doubt about what operation it performs.

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 states the required condition: 'only after explicit current-turn user authorization.' It also gives direct behavioral guidance by saying 'do not verify with read or list,' which steers the agent away from sibling tools and clarifies the expected workflow after deletion.

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 readOnly/openWorld/idempotent/destructive behavior. The description adds useful traits beyond annotations: it returns a 'complete' and 'live' snapshot, and explicitly rules out search, matching, pagination, Facts, and write variants. This is meaningful addition, though it could disclose response size or performance behavior in more detail.

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 one sentence with the primary action front-loaded and the exclusions packed into a short, scannable list. Every clause earns its place; there is no filler or redundant restating of the tool name.

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 present and a single enum parameter, the description covers the key operational constraints: complete return, live data, no pagination/search/write behavior. It is slightly incomplete in not explaining what a 'Route Catalog' is or what 'Facts' means, but that does not block a competent agent from invoking list 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 schema has no parameter descriptions (0% coverage), so the description must compensate. The description does repeat the three scope choices from the enum and relates them to the Route Catalog, but it adds little semantic detail beyond the enum values themselves. For a single required enum parameter this is adequate but not rich.

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 uses a specific verb (Return) and resource (topics, areas, or people Route Catalog), and the scope enum makes the target resource concrete. It does not, however, name the sibling 'read' tool or explain the difference between listing the full catalog and reading a single entry, so sibling differentiation is only partial.

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 phrase 'No search, matching, pagination, Facts, or write versions' gives clear when-not-to-use guidance and implies that other sibling tools handle those operations. It stops short of naming those alternatives explicitly, so an agent must infer which sibling to switch to for search or single-item reads.

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?

Beyond the destructiveHint annotation, the description discloses atomic creation, preservation of Fact dates, the invariant that at least one source Fact must remain, and the side-effect protocol to reuse returned Page Snapshots and receipts instead of re-reading. These are substantive behavioral traits an agent could not infer from the annotations alone.

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 dense sentences front-load the core action and then pack the critical post-conditions and validation guidance. Every clause earns its place: the operation scope, invariants, and the explicit don't-verify instructions. No filler or redundant restating of schema fields.

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 a complex oneOf operation schema and a nested facts array, the description covers the main behavioral caveats (atomicity, source preservation, date preservation, no post-verification) while the rich input schema covers structural details. Since an output schema exists, the description need not explain return values, and nothing essential 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 description coverage is 100%, so the baseline applies and the schema already documents operations, facts, paths, versions, aliases, and descriptions. The description only adds high-level constraints like bounded new destination and preserving dates, without detailing individual parameters. This is sufficient, but it does not add much 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 opening clause 'Move exact Facts' names the verb and resource immediately, and the two follow-up options (replace source/existing-destination descriptions, or atomically create a bounded new destination) delineate the operation's scope against create/update/rename. It also explicitly distances itself from siblings read/list by instructing the agent not to verify with them after apply.

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 clear context for when move is appropriate: moving exact Facts, optionally replacing descriptions, or creating a bounded destination. It explicitly tells the agent what not to do afterwards ('do not verify with read or list'), which is a direct usage exclusion, though it does not compare against update/rename in general terms.

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 adds useful behavioral context beyond the annotations: reads are batched ('together'), and results contain 'Facts, opaque write versions, and capacity signals.' The annotations already cover read-only and idempotent safety, so the description enhances rather than repeats 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?

Two sentences, front-loaded with the most critical usage guidance, followed by return-content context. Every sentence earns its place and there is no redundant restating of the schema or annotations.

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 a rich output schema, detailed annotations, and a single well-documented parameter, the description covers the essential decisions: when to call, how to call, and what to expect. The only minor gap is that 'Page Snapshots' is not expanded, but it is likely domain-standard enough for the intended agent.

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 already describes the 'paths' parameter with 100% coverage, including uniqueness and canonical path requirements. The description adds only a mild batch-hint with 'together,' so it does not significantly expand parameter semantics beyond the schema baseline.

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 states a clear verb+resource action: 'Read unique canonical paths together.' It also clarifies what returned files contain. However, it does not explicitly differentiate itself from sibling 'list', so the agent must infer the distinction between reading specific paths and listing the catalog.

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?

'Use before mutation unless current Page Snapshots are already available' gives explicit when-to-use guidance and names the condition under which it can be skipped. It does not explicitly state when alternatives like list should be preferred, but the usage context is clear.

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 as destructive and non-idempotent, and the description meaningfully adds behavioral guidance beyond them: reuse returned Page Snapshots and receipts, and avoid read/list verification. This is exactly the kind of operational nuance an agent needs and cannot infer from the schema alone.

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 compact sentences with no filler. The purpose is front-loaded, and the second sentence delivers critical post-action guidance. Every clause 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?

Given the annotations, rich input schema, and output schema, the description covers the essential contract: what the tool does, the snapshot requirement, per-page limits, and post-call behavior. It could slightly improve by contrasting with the 'move' sibling, but nothing critical 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 adds useful semantic context by saying 'one operation per page' and connecting the operation to 'latest Page Snapshots,' which clarifies how to construct operations and use if_version, though the individual parameter details are already well documented 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 clearly states a specific action ('Rename dynamic pages') and the resource type, with a distinguishing mechanism ('using latest Page Snapshots'). It also imposes a clear scope ('one operation per page'), making the tool's purpose 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 gives clear operational context: use the latest Page Snapshots, and after a successful rename do not verify via read or list. It does not explicitly compare this tool to siblings like move or update, so it falls short of a full when-to-use-vs-alternatives explanation.

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 adds behavior beyond the destructiveHint annotation: replacements are exact and version-based, repair is mechanical, and returned receipts/snapshots are authoritative so read/list verification is discouraged. It avoids contradicting the annotation set.

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 dense sentences with no filler. The first sentence front-loads the three operation modes and the second adds a concise workflow directive. Every clause 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 description orients the agent to all three operation types and the post-invocation behavior, while the rich schema and output schema cover parameter detail and return values. No critical calling information is missing for an agent to invoke update 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 description coverage is 100%, so the schema already documents parameters and operation discriminators in detail. The description reinforces 'exact Fact', 'latest version', and optional description, but adds no new parameter-level constraints; baseline 3 is appropriate.

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 specific operations and resources: replacing an exact Fact, updating page metadata, and mechanically repairing a page. This clearly separates the tool's three target modes and distinguishes it from generic sibling names like create, rename, or delete.

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 clear operational context: updates target existing exact Facts/page metadata, and after success the agent should reuse returned Page Snapshots and receipts rather than verify with read or list. It does not explicitly contrast update with create/add/rename/delete, but the post-invocation guidance and mode list make the intended usage fairly clear.

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