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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds substantial behavioral detail: it describes the interactive side-by-side widget, color coding for differences (red=deleted, yellow=replaced, green=inserted, blue=moved), and mandatory post-return instructions (report spot counts, don't list individual differences). This goes well beyond the annotations and provides the agent with a clear behavioral model.

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 longer than average but every sentence serves a purpose: mandatory usage, prerequisite, widget explanation, and post-return steps. It is well-structured with clear sections (MANDATORY, Before calling, After returns). Slightly verbose, but justified given the tool's complexity and interaction requirements.

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?

Given the tool's complexity (interactive widget, mandatory post-processing, prerequisite checks), the description is complete. It covers both preconditions (job_ids exist) and postconditions (report spot counts, follow cta_instruction), which is essential for correct invocation. The output schema exists, so return value details are not required in the description.

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% (all three parameters have clear descriptions), so the schema already documents the parameters. The description does not add parameter-specific semantics, but it does clarify the role of job_id_a as 'original' and job_id_b as 'modified' indirectly via the comparison context. Baseline 3 is appropriate because the schema carries the parameter documentation burden.

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 clearly states the tool compares two PDFs side-by-side, with a specific verb ('Compare') and resource ('PDFs'), and explicitly distinguishes it from analysis-based comparison by mandating its use for all document comparison requests. The title and description align, and it prevents misuse by warning against text analysis alternatives.

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 provides explicit when-to-use guidance ('When the user asks to compare, diff, or find differences between two PDFs, you MUST call this tool') and excludes alternatives ('NEVER attempt to compare documents using text analysis'). It also includes a prerequisite step (confirm both job_ids exist via check_upload_status) and post-call behavior, making usage unmistakable.

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