Comet Messenger Service

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

Annotations declare a non-read-only, non-idempotent, open-world mutation, and the description adds real behavioral context beyond that: the two-phase preview/commit pattern, the fact that nothing is booked unless confirm=true, the auth scheme (Bearer cmt_...), and the returned Comet order number. This is exactly the extra context the annotations cannot convey.

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 front-loaded sentences that each do work: purpose, call sequence, return value, credential requirement. No filler, no restatement of the title beyond what is needed.

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 tool is complex (30 params) but the schema carries 83% description coverage and an output schema exists, so return-shape detail is unnecessary. The description closes the remaining gaps: auth prerequisite, mandatory two-step confirmation, and where to get credentials. An agent has everything needed 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 description coverage is 83%, so the schema already documents nearly every parameter, including confirm, service, vehicle, when and the pickup/dropoff fields. The description reinforces the confirm gate and the preview contents but adds no syntax or defaults the schema lacks, 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?

The first sentence gives a specific verb and resource ('Book a same-day courier delivery on a Comet account') and scopes it to account holders. It is immediately distinguishable from the read-oriented siblings get_quote, order_status and recent_orders, especially since the preview-vs-confirm distinction is spelled out.

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 when-to-use workflow: call once without confirm to get a preview, show the preview to the user, then call again with identical details and confirm=true to place the order. It also routes non-account-holders to a phone number, so an agent knows the prerequisite before invoking.

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/openWorldHint, so safety is covered; the description adds genuinely useful behavior beyond that: prices are live, three named service tiers plus the vehicle are returned, and no booking side effect occurs. It stops short of noting rate limits, caching, or what happens with out-of-area addresses.

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, front-loaded with what the tool does and what it returns, then routing. The 'since 1976' clause and the street address/URL are lightly promotional, though the phone/URL routing is actionable for non-account callers.

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, return values need not be enumerated, yet the description still previews them (service tiers, vehicle). It covers purpose, side-effect profile, and the handoff path for a 13-parameter quote tool, leaving nothing an agent needs 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 description coverage is 100% across 13 params, so the schema already carries full parameter meaning; the baseline of 3 applies. The description adds no parameter-level detail (e.g. it never mentions that 'when' drives after-hours pricing or how vehicle/weight interact).

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?

Names a specific verb and resource ('Price a same-day courier delivery'), scopes it geographically (Chicago area) and names the provider. It is immediately distinguishable from sibling book_delivery, which it also explicitly references.

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?

States the boundary condition outright ('Quotes only - nothing is booked') and routes the caller: account-holder agents should use book_delivery, everyone else calls a phone number or visits a URL. Explicit when-to-use and when-not-to-use-plus-alternative.

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 establish readOnly, idempotent, and closed-world behaviour, so the safety profile is covered. The description adds genuinely useful context beyond that: the required bearer credential format (Authorization: Bearer cmt_...) and how an account holder obtains one. It does not mention rate limits or failure modes, but the auth disclosure is substantial added value.

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 outcome the caller cares about. The auth sentence carries real value, though the included phone number for obtaining a key is the least essential element.

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, the description does not need to enumerate return values (it does so anyway, which is a bonus), and it covers the one non-obvious operational requirement, authentication. For a single-parameter read tool this is essentially complete; only explicit sibling routing and error behaviour are 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 schema already documents the single order_number parameter, including that it accepts either a Comet tracking number or a request_id from book_delivery. The description adds nothing about parameters, 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?

Starts with a specific verb+resource: it reports where an order is on the account, and enumerates the concrete states returned (booked, picked up, delivered with signer/time, cancelled). It implicitly distinguishes itself from the plural sibling recent_orders by being a single-order lookup, but never names or contrasts with any sibling explicitly.

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?

Usage is implied rather than stated: an agent can infer this is the tool to call when it needs the current state of one known order. There is no guidance on when to prefer recent_orders or book_delivery, and no stated prerequisites or error conditions (e.g. unknown order numbers).

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 openWorldHint=false, so the safety profile is covered. The description adds genuinely useful auth context (Bearer cmt_ key and how an account holder obtains one), but says nothing about ordering, pagination, or what happens when the account has few or no orders.

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 first sentence is front-loaded and does the real work in one line, which is good. The second sentence mixes a legitimate prerequisite with a phone number that an agent cannot act on, so it is not pure waste but not fully earned either.

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 no explanation, and the read-only annotations plus complete parameter schema cover safety and inputs. What is missing is modest: ordering guarantees and behavior when the result set is empty.

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 both limit and active_only are already self-documenting, which sets the baseline at 3. The description adds no further meaning about the parameters, neither confirming sort order for the limit nor defining 'delivered' beyond the schema's wording.

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?

Names a specific resource and scope: the account's latest orders, returned with their status. It is distinguishable from book_delivery and get_quote, but the phrase 'with their status' partially overlaps the sibling order_status, and the description never resolves that overlap.

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?

There is no statement of when to use this tool rather than order_status, get_quote, or book_delivery, and no note on when a recent-orders listing is the right call. The only conditional content is credential acquisition, which is a precondition rather than tool-selection guidance.

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