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

The description adds useful behavioral disclosures beyond annotations: 'no files written, no network requests, no side effects' and 'read-only template metadata; writes no files and uses no network'. However, it also claims 'Inputs: category and query filter metadata' despite the schema having zero parameters, which is a contradictory and misleading claim. This undermines the transparency with a false statement about inputs, so a mid-range score is appropriate.

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 repetitious: the claim 'no files written, no network requests, no side effects' appears twice in slightly different wording. The 'Inputs' section is unnecessary and factually wrong given the empty schema, adding noise. While the use of labels (Use, Inputs, Effects) provides structure, the redundant and misleading content makes it less concise than it should be.

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 read-only list tool with no parameters and an output schema (implied by 'Returns a JSON array'), the description covers purpose, usage, safety, and return format exceptionally well. The only serious gap is the contradictory filter/input mention, which prevents a perfect score. Overall, the agent has enough context to invoke the tool correctly and interpret the result, despite this inconsistency.

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 an input schema of 0 parameters, the baseline for this dimension is 4. But the description introduces fictional inputs ('category and query filter metadata') that do not exist in the schema, which actively misleads an agent. Instead of adding meaningful parameter semantics, it creates confusion about optional filters that are not supported. Hence the score is significantly below 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?

The description opens with 'List all bundled reference templates in the Axint SDK', using a specific verb ('List') and resource ('bundled reference templates'). It further distinguishes itself from the sibling tool axint.templates.get by positioning itself as the discovery step ('use to discover valid template ids before templates.get'). The return format is also specified, making the purpose unambiguous.

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 explicitly states when to use the tool: 'use to discover valid template ids before templates.get'. It also advises 'call without filters to discover every valid id'. However, the mention of 'category and query filter metadata' is confusing because the input schema declares no parameters, so the guidance around filters is unsupported. This prevents a perfect score but the primary use case is clearly communicated.

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