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

Annotations already declare read-only, open-world, idempotent, and non-destructive behavior. The description adds useful behavioral details beyond that: it accepts up to 100 licenses, returns yes/no/check with OSADL's reason, and orders results worst first. This gives the agent a clear picture of what the tool will do.

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 dense sentence that front-loads the core purpose and packs in limits, examples, output values, and ordering. Every clause earns its place, with no redundant 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?

Given the output schema exists and annotations cover safety and open-world behavior, the description covers the remaining essentials: input formats, cardinality, output categories, reason source, and ordering. An agent has enough to select and invoke the 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 only 50%, but the description compensates by explaining both parameters: 'project' is an SPDX id or 'proprietary', and 'licenses' can include SPDX expressions with examples. This adds meaning beyond the schema, especially for the licenses array which lacks a schema 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 states a specific verb and resource: it checks whether code under each of up to 100 licenses may be included in a project under a given license, returning yes/no/check. This clearly distinguishes it from siblings like license_info and package_licenses by focusing on compatibility rather than information lookup or package scanning.

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 provides a clear context: use this when you need to evaluate whether multiple licenses or SPDX expressions are compatible with a project license. It does not explicitly name alternatives or state when not to use it, but the scenario is specific enough that an agent can infer the intended use.

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 cover read-only, open-world, idempotent, and non-destructive behavior. The description adds useful context beyond that: it accepts 'however they are written', including deprecated SPDX IDs, and caps at 20 licenses. It does not address invalid-input behavior, but the annotation coverage lowers the burden.

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 dense sentence that front-loads the core purpose and then lists output attributes compactly. There is no filler or repetition of schema details, every clause adds meaning.

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 one simple array parameter, a true output schema, and comprehensive annotations, the description provides all needed context for correct invocation. It covers input flexibility, capacity, and the scope of the returned information.

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 provides zero description for the 'licenses' parameter, so the description carries the full burden. It compensates effectively with concrete examples ('Apache License 2.0', 'GPLv3', 'New BSD') and clarifies that deprecated SPDX ids are accepted, making the semantics of the string array clear.

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 ('Identifies') and the resource ('up to 20 licenses'), and lists the specific output fields (SPDX id/name, OSI/FSF status, copyleft class, OSADL obligations). It signals the tool normalizes arbitrary license strings, which helps distinguish it from siblings, though it does not explicitly name them.

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 this is the tool to use when you have license strings in varied or deprecated formats and need normalized identification. However, it gives no explicit guidance about when to use alternatives like check_compatibility or package_licenses, nor any exclusions.

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=false, so the agent knows it's a safe read. The description adds meaningful behavioral details beyond annotations: the limit of 50, the list of ecosystems, optional version handling, the yes/no/check compatibility result, copyleft flagging, and the 'worst first' ordering. 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?

The description is a single, dense sentence with no filler. It front-loads the core action and then lists specifics efficiently. Every clause adds information: the package count, ecosystems, version handling, compatibility check, copyleft flag, and sorting. 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?

Given the tool's complexity (multiple ecosystems, version logic, compatibility assessment, copyleft flagging, ordering), the description covers all essential behaviors an agent needs to call it correctly. The output schema exists, so return format is handled elsewhere. The only minor omission is the exact meaning of 'check' in the compatibility result, but that's likely defined in the output schema and does not impede 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 only 50% (project has a description, packages does not). The description compensates by explaining the ecosystem list and that a version is optional ('a version, or the latest'), which clarifies the packages parameter's sub-fields. However, it doesn't explicitly map each schema field (name, version, ecosystem) to their roles, but the structure is obvious from the schema. The added value is moderate and helpful.

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 ('Looks up'), a clear resource ('licenses of packages'), and enumerates supported ecosystems and the optional version or latest behavior. It also explains the compatibility check and sorting ('Worst first'), which clearly distinguishes it from sibling tools like license_info (which likely just returns license data) and check_compatibility (which might check specific compatibility rules).

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 provides clear context: up to 50 packages, which ecosystems, and that it checks compatibility against a project license when 'project' is provided. It implies when to use (when you need license compatibility screening) but does not explicitly name alternatives or exclusions. Sibling tools exist but are not referenced, so there's a slight gap in routing, but the context is strong enough.

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