plc_compare_projects

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

Annotations already cover read-only, idempotent, non-destructive and closed-world behavior, and the description adds substantial context on top: every ZIP member delta is retained, fingerprints are bounded, output is paginated, and logical paths match objects across ID changes. It further discloses that ambiguous matches and unacquired content are surfaced explicitly and that results do not prove functional equivalence or build/IDE fidelity, which prevents an agent from over-reading a 'no differences' result.

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?

Four compact sentences with the core comparison scope front-loaded, followed by output characteristics and then caveats in a logical progression. Every clause carries information, though the density of the second and third sentences makes them harder to parse than a bulleted framing would 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 high-complexity comparison tool this covers the essentials: comparison domain, matching semantics, output bounding, and explicit limitations. With an output schema present it does not need to describe return values, but the absence of any guidance on the before/after input format leaves the most important call-time detail unstated.

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 50%: limit and offset are documented in the schema, while before and after carry only titles. The description partially compensates by characterizing the inputs as two local SMC2 copies and by mentioning pagination, but it never states what form before/after take, such as directory paths or ZIP paths, or how the two sides are ordered.

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 states a specific verb and resource: comparing two local SMC2 copies across objects, variables, ST/LD and tasks, plus ZIP member retention. That is far more precise than a bare 'compare projects', though it never names plc_compare_files to draw the project-vs-file boundary explicitly.

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?

Usage is implied by the phrase 'two local SMC2 copies', which signals this tool is for project-level comparison of local copies rather than arbitrary files. It also sets a scope boundary by disclaiming functional equivalence, build success and IDE round-trip. However, it never explicitly says when to prefer it over plc_compare_files or what prerequisites the copies must satisfy.

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