AgentTwin Documentation

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description contributes the 'published' qualifier, hinting that unpublished guides are not readable, but it does not describe the returned content shape or error behavior for stale paths.

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?

A single front-loaded sentence with no filler: the action, the resource, the lookup constraint, and the provenance of the path all appear before the period.

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 one-parameter, fully annotated read tool with no output schema, the definition covers what an agent needs to invoke it. The only real gap is a hint about the response (raw Markdown body vs. metadata), which is minor given the tool's simplicity.

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 carries the burden for the single path parameter. It does add real value by naming where valid paths come from and insisting on exactness, but it never illustrates a path format (for example, a relative .md path) or explains what happens on a mismatch.

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 (read) and a specific resource (a published AgentTwin Markdown guide) qualified by an exact-path lookup. It distinguishes itself from the sibling search_docs by framing that tool as the source of paths, so an agent can tell the two apart without opening either 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?

The phrase 'exact path returned by search_docs or resources/list' tells the agent that discovery must happen first and that fuzzy paths will not work. There are no explicit when-not-to-use exclusions, but the workflow context is clear enough to call correctly.

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

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds one valuable behavioral boundary in 'Does not access customer data', but says nothing about result ranking, result limits, pagination, or what a match looks like.

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 sentences, zero waste, with the verb and resource front-loaded and the scope disclaimer trailing. Every sentence earns its place and nothing is buried.

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 no output schema and an undocumented parameter, the description should say more about how queries are matched and what comes back. It is adequate for an agent to call it, but leaves avoidable gaps around query semantics for a search tool whose only input is a free-text string.

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?

The single required parameter 'query' has 0% schema description coverage, so the description carries the full burden and fails to explain it. It does not say whether query is keyword, phrase, or substring matching, nor how the 200-character cap or empty results are handled.

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 (Search) and enumerates the resource scope precisely: public AgentTwin guides, CLI commands and operation contracts. The scope is clear enough to separate it from read_doc in practice, though it never names the sibling or explains the search-vs-read relationship 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 only implied: an agent can infer this is the discovery step before read_doc, but the description never states when to use this versus read_doc, nor when it should be avoided. The one exclusion ('Does not access customer data') bounds scope rather than routing between tools.

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