maket_html

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses failure modes (set rejects whole payload, patch rolls back individually), side-effect expectations (check has no side effects), prerequisites (context_token required with charte), layout override eligibility, and detailed compliance rules. It also explains check statuses (OK, tight, overflow, unchecked) and what triggers them, making behavior highly transparent.

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 long but well-structured: it leads with a 'When to use' summary, then details compliance rules, layout override, state-backed document rules, and an action table. Each section adds necessary information, though there is some redundancy with schema content (e.g., data-id requirement appears in both). Given the tool's complexity, the length is justified and the organization helps an agent parse it.

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?

The tool has no output schema, so the description must explain return values and behaviors. It does so thoroughly: get's format parameter (html/text), check's statuses and next steps, patch's rollback behavior, and set's validation approach. It also covers edge cases like unchecked validation and the layout-override caveats. For a tool with this many actions and rules, the description is impressively complete.

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 all parameters are already described in detail (e.g., ops structure, html example, context_token purpose). The description adds some behavioral context (e.g., when context_token is required, layout override constraints), but most of it complements rather than meaningfully extends the schema. The baseline of 3 is appropriate because the schema does the heavy lifting and the description adds incremental value.

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 'read and write page HTML' and then enumerates four distinct actions (set, patch, get, check) with precise verbs and targets. This clearly identifies the resource (page HTML) and differentiates the tool's internal operations, though it doesn't explicitly contrast with sibling tools. The action table makes the tool's purpose unmistakable.

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 says 'Pick set for the initial skeleton, patch for iterative edits, get to read, check to measure overflow without writing', which gives excellent action-level usage guidance. It also implies when not to use check ('without writing'). However, it does not name alternative sibling tools (e.g., maket_page, maket_canvas) for scenarios where this tool should not be used, so it's clear but not fully complete on external alternatives.

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