Delimit Tdqs Lint

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

The description claims 'Side effects: none. Pure read-only static analysis via ast (no import, no execution)' and explicitly says it does not write ledger/evidence/notify. However, the annotations declare readOnlyHint=false, which signals the tool is not read-only. This direct contradiction undermines the agent's trust in whether invoking the tool can mutate state.

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 well-structured with clear 'When to use', 'When NOT to use', 'Sibling contrast', and 'Side effects' sections, and the main purpose is front-loaded. It is slightly longer than necessary — the ticket reference (LED-2108) and some repetition of the sibling distinction could be trimmed — but every substantive sentence earns its place.

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 tool with two optional parameters and an output schema, the description covers purpose, operational scope (file pattern), non-goals, side effects, and alternatives. No critical operational information for an agent selecting or invoking the tool is missing; the only issue is the annotation contradiction already scored.

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 the schema already documents both parameters. The description adds some context for target_file by mentioning it operates on Python files with @mcp.tool() decorators, but it does not explain the 'human' parameter beyond the schema. Baseline 3 is appropriate because the schema carries the parameter-documentation load.

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?

Description opens with a specific verb-resource pair: 'Score MCP tool docstrings against the 6 TDQS dimensions.' It also names sibling tools it is not, noting it differs from delimit_lint (OpenAPI specs) and delimit_spec_health (spec quality scoring). An agent can clearly distinguish this from the many delimit_* siblings.

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?

Provides an explicit 'When to use' ('as a CI gate before publishing the MCP server') and 'When NOT to use' (runtime tool selection or policy decisions), and names alternatives for those cases (delimit_lint for OpenAPI specs, delimit_gov_evaluate for policy). This gives the agent unambiguous selection criteria.

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