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

With zero annotations, the description carries the full burden and does well: it discloses the ticket-issuance side effect, the blocking failure mode ('risk="block" and no ticket'), and the destructive semantics of purge. It omits ticket lifetime/single-use enforcement details and any permission or irreversibility warnings for purge.

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 ticket mechanics, then details each scope in one clause. Dense and largely waste-free, though the final blocking sentence could be folded into the scope discussion rather than trailing.

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 six-parameter, no-annotation, no-output-schema mutation-gating tool, the description covers the decision-relevant surface: scope semantics, recursion constraint, purge selectors, and the block outcome. It stops short of explaining what the returned ticket is and how it is consumed downstream, which an agent would need to complete the workflow.

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 0% with six parameters including a free-form scope string, so the description must do all the work and does: it supplies the two valid scope values (absent from the schema), explains recursive, and enumerates the mutually alternative purge selectors (batch_ids, older_than_days, all=true). Only 'paths' is described implicitly via 'moving paths into the .del directory', which is still adequate.

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 compound verb+resource: validates a delete request and issues a one-time ticket, then breaks down the two scopes (trash vs purge). It never names the sibling tools that actually execute the deletion (trash_paths, purge_del), so the two-phase relationship is implied by 'previews' and 'ticket' rather than stated outright.

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?

Explains per-scope when to use: scope="trash" for moving paths into .del, scope="purge" for permanently removing .del batches, with recursive=true required for non-empty directories. It gives no explicit 'do not call trash_paths/purge_del without a ticket' routing instruction, so the sequencing to siblings stays implicit.

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?

With no annotations, the description carries the full burden and does disclose the most safety-critical traits: permanence/irreversibility, ticket provenance, and a staleness guard that refuses changed batches. It omits other meaningful behaviors such as what accept_warnings gates, whether warnings block execution, and 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?

Three short sentences, front-loaded with the action and its permanence. Every sentence carries information (action, precondition, rejection rule); nothing is padded.

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, irreversible, 5-parameter tool with no annotations and no output schema, the description covers provenance and atomicity but leaves the warning-acknowledgment flow, selection-mode interactions (`all` vs `batch_ids` vs `older_than_days`), and the result shape unexplained.

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 all five parameters are bare names. The description adds real meaning for `ticket` (must come from preview_delete with scope="purge") and implies batch_ids derive from the preview, but says nothing about `all`, `older_than_days`, or the safety-relevant `accept_warnings`.

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 combination with emphasis on irreversibility: "Permanently delete .del batches selected by the matching purge preview." The preview-derived selection model distinguishes it from a generic delete, though it never names trash_paths as the non-permanent sibling, so an agent must infer the contrast.

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 prerequisite: the ticket must originate from preview_delete with scope="purge", which effectively defines when the tool is callable. It also documents a rejection condition (batches added/changed after preview), but offers no guidance on when to prefer trash_paths instead of permanent purge.

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?

With no annotations, the description carries the whole burden and does disclose real behavior: the target is a .del directory (implying recoverable rather than permanent removal), and paths modified after preview are refused, a meaningful staleness guard. It omits what accept_warnings does, whether partial failures are possible, and what the caller gets back.

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 short sentences, no filler, and the core action is front-loaded before the preconditions. Every sentence adds a distinct constraint.

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 four-parameter mutation with no annotations, no output schema, and 0% schema coverage, the description covers the workflow gate well but leaves accept_warnings unexplained and says nothing about outcome or recoverability. Adequate, not complete.

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 0%, so the description must compensate and it partially does: it constrains 'paths' and 'recursive' by requiring them to match the preview, and explains 'ticket' by origin. 'accept_warnings' is never mentioned anywhere, leaving one of four parameters with no semantics at all.

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 verb and destination: 'Move previewed paths into the workspace .del directory.' The word 'previewed' and the ticket requirement implicitly position it downstream of preview_delete, but siblings are never named, so differentiation relies on the agent already knowing the workflow.

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 a hard precondition: the ticket must come from preview_delete with scope="trash" and matching paths and recursive flag, which tells the agent to call preview first. It does not explicitly contrast with purge_del or say what to do when paths changed after preview beyond 'refused'.

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