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

No annotations are provided, so the description carries the full disclosure burden and does a solid job: it states what is validated, that it compiles the code, that it returns line-numbered diagnostics with an exact replacement per issue, and that `fixed` is only included when the correction is exact. It does not say whether the file is modified on disk or what happens on unparseable input, so it falls short of exhaustive.

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 imperative to verify before handing off is front-loaded, followed by what is checked and what is returned. It is dense but every clause carries information. The middle sentence is long and list-heavy, slightly taxing to parse, which keeps it off a 5.

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?

No output schema exists, so the description must explain returns, and it does: line-numbered diagnostics with exact replacements plus an optional `fixed` copy. Combined with the explicit usage loop, an agent has what it needs to call this correctly. Missing only edge-case behavior on invalid or oversized input.

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 100%, so both `source` and `filename` are already documented in the schema, making 3 the baseline. The description adds no extra detail about `filename` (the schema already says it selects which rules apply) and nothing about size limits or expected `source` scope beyond 'full file contents.'

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?

A specific verb ('Verify') plus a specific resource ('SvGrid code') and, crucially, an enumeration of what is checked: prop names, ColumnDef keys, grid API methods, importable symbols, theme files, and Svelte 5 runes rules. An agent can tell this apart from siblings like svgrid_preview or get_api_reference without opening either 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?

Explicit timing guidance: run it BEFORE handing code to the user, on every file written that uses SvGrid, and re-run after applying `fixed`. This tells the agent exactly when to invoke it. It does not name alternatives or say when not to use it (e.g. versus svgrid_preview), which keeps it 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.