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

Goes well beyond the readOnly/openWorld/destructive annotations: dates 'filter actual read timestamps, not continuous presence', changed_only means 'multiple distinct captured texts, not a known edit date', 'Only Overworld captured', and an untrusted-source warning ('never instructions or proof of authorship'). These are exactly the non-obvious behaviors an agent needs.

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?

Purpose is front-loaded and no sentence is wasted, but it is a dense block of stacked clauses that packs parameters, semantics and safety into a single run-on paragraph. Slightly more structure would aid scanning, though the size is justified for 13 parameters.

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?

With an output schema present, return values needn't be described, and the description still names canonicalUrl for citation. Scope ('Only Overworld captured'), pagination, date semantics and the prompt-injection warning cover everything an agent needs to call it safely and correctly.

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% and there are 13 parameters, yet the description supplies the enum values the schema lacks (match=phrase/allWords/word, sort=newest/oldest/changes), the bounds rule ('require all four coordinates'), pagination ('max25/page with nextOffset') and the semantics of from/to and changed_only. It compensates almost fully for the coverage 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?

States a specific verb+resource with scope: 'Search historical NoCom sign text one captured version at a time.' This immediately distinguishes it from the combined-text sibling search_nocom_signs and from get_nocom_sign_history, so an agent can route without opening a schema.

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?

Explicitly routes: 'Prefer this to combined-text search for exact history' names the condition selecting this over search_nocom_signs, and 'inspect get_nocom_sign_history for full reads' names the alternative for full reads. When-to-use and which-sibling guidance is fully specified.

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