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

No annotations exist, so the description carries the full burden. It does disclose valuable behavior: it normalizes whitespace, case, quotes, bullets, and copyright lines before matching, and it matches against 32 known licenses rather than parsing generically. What it omits is the outcome for non-matching text, whether a confidence or score is returned, and how `restrict` interacts with an unknown id — all relevant for a no-annotation 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?

The core purpose is front-loaded in the first clause before the normalization and license-list detail. The long enumerated license list earns most of its place because it defines the supported set exactly, though the sentence is malformed — the parenthetical list of licenses is never closed, ending at 'PostgreSQL' without a closing parenthesis.

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, so the description should indicate what comes back, but it never says whether the result is a bare SPDX id, a match confidence, or an empty result on failure. For a two-parameter identification tool the input side is well covered, but the return contract and the no-match case are gaps an agent must guess at.

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 `text` and `restrict` are already documented in the schema, which sets the baseline at 3. The description adds context that the tool normalizes the input text heavily (so imperfect formatting is fine), but it never mentions `restrict` or explains how a restricted candidate set affects matching.

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 opens with a specific verb and resource ('SPDX license identification from LICENSE text') and then quantifies the mechanism (normalization plus distinctive-phrase matching against 32 named licenses). The enumerated license set (MIT, Apache-2.0, GPL variants, etc.) makes the scope unambiguous and clearly separable from a sibling like ai-bom-license-resolver, which is about dependency license resolution rather than raw LICENSE text identification.

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 by 'from LICENSE text' and the mention of normalization, which tells the agent this is for raw license file content rather than package metadata. However, there is no explicit when-to-use/when-not guidance, no mention of what to do if no license matches (unknown/absent result), and no statement of what happens if `restrict` contains an unrecognized SPDX id.

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