propose_highlight

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

With no annotations, the description carries the full burden; it does disclose the two most important behaviors: the search is normalization-aware and it performs no PDF mutation (read-only). It does not disclose failure behavior when no match is found, nor what a successful 'proposal' actually is, which matters for a propose/apply tool pair.

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?

Two short sentences, zero filler, with the read-only constraint front-loaded and the edge-case rule second. Nothing could be removed without losing information.

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 4-parameter tool with no annotations and no output schema, the description covers the mutation-safety question and the key parameter semantics, but omits the return shape ('locations' is vague) and the relationship to apply_highlight, leaving the propose/apply lifecycle incomplete.

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 0%, so the description must compensate, and it does for the non-obvious parameters: 'exact normalized words' clarifies exact_quote's matching semantics and the '1-based occurrence' rule clarifies occurrence's conditional purpose. file and page remain undocumented, but they are self-evident.

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?

States a specific verb ('find') and resource ('exact normalized words'), and its locations, plus a clear scope qualifier ('WITHOUT modifying any PDF'). This distinguishes it in spirit from apply_highlight, but the sibling is never named, so an agent must infer the propose/apply split from naming convention alone.

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?

It gives a conditional rule for the repeated-passage case ('specify 1-based occurrence explicitly'), which is genuine usage guidance. However it never says when to prefer this over apply_highlight or that the result is meant to feed a subsequent apply step, so the workflow context is only implied.

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