MesColis Shipping

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds critical context beyond annotations: it requires the user to connect their account, returns each carrier/service with price, currency, and transit days, and warns that prices are live and account-specific (do not cache). This covers auth needs, output shape, and a key operational constraint.

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 sentences with zero waste: purpose and scope front-loaded, followed by return fields, auth/alternative routing, and caching caution. Every sentence contributes necessary information without redundancy.

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 9 parameters (6 required), no output schema, and rich annotations, the description is complete: it explains purpose, return values, auth requirements, caching behavior, and the alternative for unsigned users. The schema fully covers parameter semantics, so nothing critical is missing for 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?

Schema description coverage is 100%, so the schema already documents all 9 parameters with units and examples. The description adds only the phrase 'one parcel' and does not provide any parameter-level guidance beyond what the schema provides; 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?

States a specific verb (Compare) and resource (live shipping rates) for one parcel across every carrier on the signed-in account, and explicitly distinguishes it from get_shipping_quote for users without an account. The agent can tell exactly what the tool does and how it differs from the sibling.

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 (signed-in account, live account-specific prices) and when not to use (for someone without an account use get_shipping_quote, which needs no sign-in). It also adds a caching caution, leaving no ambiguity about context or alternatives.

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, idempotent, open-world behavior, so the bar is lower; the description still adds useful details about result ordering ('nearest first') and the fields returned (address, distance, capabilities, map link). The opening-hours caveat is a genuine behavioral note that 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?

Front-loaded with the core action and scope, then the network coverage and result contents. Four sentences with essentially no filler; the opening-hours sentence is the only borderline item but it is actionable guidance.

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 compensates by describing what comes back (nearest-first ordering, address, distance, available services, map link). Combined with the fully documented schema, an agent has everything needed to call this 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% and every parameter already has a description, including enums for lang and network and the 1-5 bound on max_per_network. The description only restates the optional network filter, adding no syntax or format detail beyond the schema, 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 and resource ('Find places near a Canadian postal code where a parcel can be dropped off or picked up') and enumerates the covered networks. This is clearly distinguishable from siblings like track_package or compare_shipping_rates without inspecting 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 clear context for use (locating drop-off/pick-up points near a postal code, no account needed) and explains the optional single-network narrowing. It does not name alternatives or state when not to use it, but the sibling set is far enough away that no confusion is likely.

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, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real value beyond that by enumerating the returned payload (addresses, carrier, service, cost, status) — the only return-shape signal available, since there is no output 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?

One sentence, front-loaded with the action and the lookup key, with the return contents following. No filler and nothing redundant with the title.

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 single-parameter read tool with rich annotations, this covers what is needed: what it fetches, by what key, and roughly what comes back. The only gap is the absence of routing guidance among the several tracking/list siblings.

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 even supplies a format example ('SHP-9FD8D9B5'). The description's 'by its ID' adds no meaning beyond that, 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?

Specific verb ('Retrieve') plus resource ('a single shipment by its ID'), and the word 'single' implicitly contrasts with the list_shipments sibling. It stops short of naming any sibling explicitly, so differentiation is left partly to inference.

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 'by its ID' phrasing implies the caller must already have an identifier, which is a useful prerequisite signal. However, it never states when to use this versus list_shipments, track_package, or track_parcel, so the agent must infer the boundary from names alone.

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 read-only annotations, it discloses that no account is needed, prices are public rates at quote time, and the response includes up to six cheapest services with price, transit time, and a website link for buying the label. This gives the agent useful behavioral context for interpreting and presenting results.

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 front-loaded with the core purpose, then adds only relevant usage and return details. Despite being several sentences, each part contributes useful information for invoking or interpreting the tool.

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 adequately explains what is returned: up to six cheapest services, price, estimated transit time, and a quote link. Together with the annotations and fully documented schema, an agent has enough context to call and present this tool 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 the schema already documents each parameter. The description still adds meaningful guidance beyond the schema, especially unit conversion for weight and dimensions and the default 30 x 20 x 10 cm box assumption when dimensions are omitted.

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 and resource: get live shipping prices for one parcel from several named carriers. It clearly distinguishes this from compare_shipping_rates by positioning that sibling as the account-price alternative.

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?

It explicitly says when to use this tool: public rates, no account needed, origin/destination postal codes and weight required. It also names the alternative when the user is signed in: compare_shipping_rates returns their own account prices instead.

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=true, idempotentHint=true and destructiveHint=false, so the read-only nature is structured data, not new information. The description does add one genuine nuance — that the server as a whole cannot create/change/delete addresses, telling the agent not to hunt for a mutation sibling — but says nothing about pagination behavior, result ordering, or empty results.

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 short sentences with zero filler, and the core action is front-loaded before the capability 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 simple, annotation-covered, zero-required-param list tool with no output schema, this is nearly complete. The only real gap is that it doesn't hint at what an address record contains or that an empty list is a valid result.

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%: limit (max 100, default 50) and offset (default 0) are fully documented in the schema. The description adds nothing about them, which is acceptable but earns only the 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?

States a specific verb and resource ("List saved addresses") plus the source ("account address book"), which is unambiguous. None of the siblings (rates, shipments, tracking, drop-off points) overlap with address retrieval, so the tool is easily separable even without an explicit sibling callout.

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 only implied: an agent infers it should call this when it needs an address from the address book, e.g. to feed a shipping quote. There is no explicit when-to-use, no prerequisites, and no statement about when this is preferable to other lookup paths.

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, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: results are scoped to the authenticated account and returned newest first, which affects how an agent consumes the list. Return shape and paging limits are left to the 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?

Three short sentences, zero filler, with the core operation and ordering front-loaded and the sibling reference last. Every clause adds 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-param list tool with no output schema and full annotation coverage, this is nearly complete: purpose, scope, ordering, filtering and the sibling alternative are all present. It does not describe the shape of returned shipment entries, which an agent must infer.

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 would be 3, but the description adds value by naming example status values ('Delivered', 'In Transit') where the schema declares no enums, and by confirming limit/offset are a paging pair. That meaningfully reduces guesswork on the unconstrained status string.

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 plus scope ('on the authenticated account') and default ordering ('newest first'). It explicitly distinguishes itself from get_shipment, so an agent can separate the list operation from the single-record sibling without opening a 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 clear routing guidance with 'Use get_shipment for the full record of one shipment' and notes paging/filtering support. It stops short of covering the other nearby siblings (track_package, list_addresses), so the when-not coverage is good but not exhaustive.

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 read-only, idempotent and open-world behavior, so the description only needs to add context — and it does: no authentication required, which carriers are covered, and the 'most Canadian carrier numbers' limitation that signals partial coverage and possible misses.

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, then progressively adds coverage, return contents, and usage trigger. The carrier enumeration is slightly long but does real work by defining supported inputs.

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 correctly summarizes the return payload (status, delivery date, carrier scans, tracking link). It is nearly complete for a simple read tool; only the track_parcel overlap and not-found behavior are unaddressed.

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 both parameters (including the lang enum and its defaults) are already documented. The description adds no parameter-specific detail beyond the concept of a tracking number, 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 and resource ('Track any parcel by its tracking number') and scopes carrier support precisely. However, it never distinguishes itself from the sibling track_parcel, which an agent choosing between the two would need.

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 this whenever someone asks where a parcel is' gives an explicit trigger condition, and 'No account needed' removes a common prerequisite question. It stops short of naming track_parcel or saying when that sibling is preferable.

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 and destructiveHint=false, so the safety profile is covered. The description adds useful context beyond annotations: it requires a connected account, lists what is returned (status, ETA, shipment id, checkpoints), and notes that supplying the carrier speeds up lookup. It does not describe failure modes or rate limits, but it is strong for a read-only lookup.

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 sentences, each earning its place: purpose/scope, return values, prerequisite, and alternative/optional-parameter note. It is front-loaded with the core operation and contains no redundancy.

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?

There is no output schema, but the description compensates by naming the key return fields. It covers the account prerequisite, the alternative tool for no-sign-in tracking, and the optional carrier optimization. An agent has everything needed to invoke 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 the schema already documents both parameters. The description adds value by clarifying the account context for the lookup and that the carrier parameter is optional but improves performance, which is not 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 states a specific verb and resource ('Look up the live status and checkpoint history of a parcel') and clearly bounds scope to the signed-in account. It explicitly distinguishes itself from the sibling track_package, so an agent can select correctly 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?

It gives explicit when-to-use guidance ('on the SIGNED-IN account'), names the alternative ('track_package') and the exact condition for choosing it ('to track any parcel without signing in'). It also states the account-connection prerequisite.

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