Artyfile Music Licensing

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

The description adds substantial behavioral detail beyond the annotations: the payment requires user browser approval due to EU PSD2, the agent cannot complete payment itself, and the session/reservation expires after 1 hour. This gives an agent a realistic model of the tool's side effects and limitations.

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 sentences with no filler. It front-loads the core purpose, then packs the essential behavioral caveats and expiration policy into a compact, readable format.

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 checkout-creation tool with no output schema, the description adequately explains what is returned (Stripe URL and order publicId), what the agent should not do, and the 1-hour expiration. The main missing detail, explicit routing to get_order_status, is minor because the publicId-for-polling mention already signals the next step.

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 80%, so the schema already documents most parameters. The description adds no parameter-level detail beyond the schema, which is acceptable at this coverage level; locale remains undocumented in both schema and description.

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 the action ('Create a checkout') and resource ('for one track'), and it distinguishes this tool from the read-oriented siblings by describing the Stripe hosted-payment URL and order publicId. An agent can tell this is the purchase-initiation tool without needing to inspect 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?

The description gives clear operational context: the user must open the returned URL, approve payment in a browser, and the agent never completes payment. It implies polling with get_order_status via the publicId, but it does not explicitly name that sibling or state when not to use this tool.

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 read-only, idempotent, and non-destructive; the description adds useful behavioral detail ('link re-issuable anytime, no cookies needed') and clarifies exactly which artifacts are returned. No contradiction with annotations.

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 dense sentence front-loads the main purpose and lists deliverables economically. Slightly busy, but there is no filler; it could add a publicId hint without much cost.

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-only tool, the description covers invocation context and the key return artifacts. It does not describe the response shape or error conditions, but the absence of an output schema makes this a minor gap rather than a blocker.

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?

With 0% schema description coverage and only one parameter, the description should explain what publicId is and how to obtain it. It only implies it identifies the paid order; it does not state the expected value, format, or provenance.

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?

Description uses a specific verb and resource: it returns download and document URLs for a paid order, enumerating the WAV download, PDF invoice, and PDF licence/certificate. This clearly distinguishes it from siblings like get_order_status or get_track.

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 'PAID order' qualifier gives context that this is for completed purchases and that the link can be re-issued anytime, but it does not explicitly name alternatives or state when not to use this tool versus get_order_status or get_track.

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 that this is read-only, idempotent, and non-destructive, lowering the bar. The description adds useful behavioral context by specifying what the summary contains, including that it is machine-readable and links to the binding Terms & Conditions. No hidden or surprising behavior is implied.

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 sentences, front-loads the core function, and packs pricing, licence types, restrictions, and external references into a tight, readable format. Every clause contributes meaningful information with no filler.

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 zero-parameter read-only tool with no output schema, the description covers the essential return contents well: tier names, prices, licence conditions, restrictions, and links to full terms. It stops short of describing the output format or field names, but that is a minor gap given the simple, informational nature of the 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?

The tool has zero parameters, so there is no parameter semantics for the description to add. With an empty input schema and a 100% description coverage baseline, nothing is missing; the description appropriately focuses on the output rather than inputs.

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 and resource: retrieving a machine-readable summary of the Artyfile licence tiers. It goes beyond the name by enumerating the exact contents (prices, restrictions, links), and the content obviously differentiates it from siblings like create_checkout or search_tracks.

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 implies when to use the tool — whenever an agent needs licence terms, pricing, or Cover-Edition restrictions — but it does not explicitly state conditions, exclusions, or alternatives. Sibling tools are not referenced, so an agent must infer the appropriate context from the description 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?

Even though annotations already mark this as read-only, idempotent, and non-destructive, the description adds important behavioral context: the paid-state payload includes downloadUrl, invoiceUrl, and certificateUrl, and pending orders expire after 1 hour. This goes well beyond the annotations.

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 core action, then the conditional payload, then the polling cadence and expiry rule. Every sentence earns its place with no repetition or filler.

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?

Despite having no output schema, the description explains the important return fields when paid, the polling interval, and the expiration condition. For a simple one-parameter read-only poller, this is enough for an agent to invoke and interpret the result 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 description and there is only one parameter, publicId. The description restates that the tool polls an order by publicId but does not explain where this ID comes from or how to format it. Because the parameter name is self-describing and there is only one, this is adequate but not enriched.

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 the specific action: poll an order by publicId. It also distinguishes this from siblings by describing the status-polling behavior and the conditional payload when paid, so an agent can tell it apart from get_download_link or get_track.

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 concrete usage guidance: poll roughly every 15 seconds, stop when paid, and treat orders older than 1 hour as expired. It does not explicitly name alternatives or state when not to use this tool, so it stops short of a 5.

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 destructiveHint, covering the safety profile. The description adds value by listing specific behavioral outputs (preview URL, human product page) and details of the response, but it does not add substantial new behavioral disclosures beyond what annotations provide. The safety traits are consistent with the 'read' nature of the tool.

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, front-loaded sentence that immediately states the core purpose and lists key elements. There is zero wasteful prose; every word contributes to understanding what the tool does and what it returns.

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 single-parameter lookup with no output schema, the description provides everything an agent needs: it explains input (productId or slug), output (full details including specific fields), and safety (via annotations). Nothing essential 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% because the only parameter 'id' already includes a description: 'productId (from search_tracks) or the track slug'. The description's mention of 'by productId or slug' simply reinforces the existing schema documentation without adding new semantic details. Baseline 3 is appropriate given the high coverage.

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 ('get'), a resource ('one track'), and explicitly enumerates the included content (metadata, prices, licence scope, preview URL, human product page). It clearly distinguishes this from siblings like search_tracks (search) and get_download_link (download) by focusing on 'full details' for a single track.

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 clearly implies the primary use case: retrieving full details for a specific track when you have a productId or slug. It does not explicitly mention alternatives or exclusions, but the specificity of 'Full details' and the parameter description reinforce the intended use. Given the sibling list, an agent can infer this is the detailed lookup vs. search or download tools.

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, so the bar is lower. The description adds valuable behavioral context beyond annotations: results are ranked, prices are included, result ids are create_checkout productIds, and licenseScope 'master_only' denotes Cover Editions lacking sync licenses. This materially changes how an agent should interpret and use the output.

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 a single targeted paragraph with rich, non-redundant content. Every clause contributes: catalog scope, quality guarantee, ranking/pricing, id integration, and a critical licensing caveat. It could be slightly tighter, but the density is appropriate for the information conveyed.

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 lack of an output schema, the description explains key return aspects: ranked tracks with prices, productId linkage, and licenseScope caveats. It doesn't detail the full track result shape or how limit affects ranking, but the most decision-critical facts for correct invocation and interpretation are present.

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 only 25%, with only the query parameter documented. The description adds no meaning for the mood, genre, or limit parameters — it doesn't mention them at all. With low schema coverage, the description was expected to compensate, and it failed to do so.

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 the tool searches a licensable music catalog and returns ranked tracks with prices. It distinguishes itself from siblings like get_track (single-track fetch) and create_checkout (purchase flow) by explicitly linking result ids to create_checkout productIds.

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 strong context for when to use the tool: search the catalog first, then use result ids for create_checkout. It also warns against selecting master_only results for media projects. It doesn't explicitly contrast with get_track or state when to avoid searching, but the downstream guidance is clear and actionable.

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