td_project_diff

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

With no annotations provided, the description carries the full burden of disclosing behavior. It thoroughly explains what the diff reports (operators, DAT code lines, moves), how parameter changes are presented (constant vs expression/bind text, with no marker), and the semantics of + and - signs relative to defaults. It also explains how to recover a value via td_project_text. This goes well beyond a basic 'compares files' statement and gives the agent a precise mental model of the tool's output.

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 efficiently organized: a one-sentence purpose statement, a list of report types, a note on moves, a usage example, and then a detailed explanation of parameter-line semantics. Every sentence adds value, and the most important information (what it does and what it reports) is front-loaded. It is long but not verbose; each paragraph serves a distinct purpose.

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 diff tool with nuanced output, the description covers the main functionality comprehensively: what is compared, what kinds of changes are reported, how moves are handled, how to interpret parameter changes, and how to revert values. The only missing details are the two boolean parameters, but the core behavior is fully explained. The presence of an output schema (indicated in context signals) likely fills any remaining gaps about return structure.

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 0%, so the description must explain parameters. It clarifies that 'before' and 'after' should be td_snapshot files, which is helpful. However, it never mentions the 'show_moves' and 'include_text' parameters or their effect on output, even though the description discusses moves and text diffs in other contexts. The partial coverage of the required parameters is useful but leaves two booleans undocumented, so the description does not fully compensate for the schema gap.

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 clear verb ('Compare') and resource ('two .toe/.tox files') and immediately states the tool's core function: reporting what actually changed. It lists specific change types (added, removed, retyped, rewired, re-parameterised) and even distinguishes moves from real changes, making its purpose unambiguous and distinct from any sibling tool.

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 gives a concrete usage scenario: comparing a live branch by passing two td_snapshot files of the same COMP. It explains how to interpret parameter lines and how to restore values. However, it does not explicitly mention when not to use this tool or name alternative tools (e.g., td_variant_diff), so it stops short of full exclusionary guidance.

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