HenryKnows

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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering safety. The description adds useful behavioral context beyond that: it discloses the response latency (10–40 seconds), that answers are cited, and gives a phrasing instruction. This goes beyond what annotations provide, though it doesn't mention session handling or error cases, which are handled by the schema.

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 only two sentences: the first delivers the core purpose, the second adds critical usage and timing information. It is front-loaded, with no repetition of schema or annotation fields, and every sentence adds value. Excellent concision.

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 question-answering tool, the description covers purpose, latency, response style, and phrasing constraints. It does not explicitly differentiate from siblings, but the schema and annotations cover parameter details and safety. The output schema is absent, but the cited-answer behavior is stated. Overall, it is adequately complete for an agent to call it 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 100%, so the baseline is 3. The description adds meaningful guidance on the 'question' parameter by instructing the agent to ask in the person's own terms and avoid identifiers, which clarifies expected content in a way the schema's field description does not fully capture. This modest addition justifies a 4.

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 a specific verb ('Ask') and resource ('HenryKnows'), and defines the exact domain (F-1/J-1 immigration, SEVIS, OPT, CPT). This distinguishes it from siblings like 'search_sources' and 'connect', which have different functions. Even without naming them, the purpose is unmistakable.

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 includes guidance on how to phrase questions ('Ask in the person's own terms; do not add identifiers') and notes the response time, but it does not explicitly state when to prefer this tool over its siblings 'connect' or 'search_sources'. There is no direct comparison or exclusion, so the selection criteria are left to inference.

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 readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond the annotations: the tool turns the page light green, establishes a session, and can be omitted because other tools connect as well. It does not describe failure modes or what happens with an invalid session code, but the core behavior is transparent.

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?

Three sentences with no wasted words. The most important guidance ('Call this first if...') is front-loaded, and the optionality is stated immediately after. Every sentence earns its place.

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 single-optional-parameter tool with full schema coverage and safety annotations, the description is nearly complete. It explains the purpose, the effect, the session handoff, and when to call it. The only minor gap is that it doesn't describe what happens if an invalid session code is provided, but that is not essential for correct invocation.

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%, so the schema already documents the session parameter. The description adds value by explaining where the session comes from ('from an earlier result, or the session code the person gave you') and that omitting it starts a new one. This goes beyond the schema's description.

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 ('Connect'), a specific resource ('the HenryKnows page the person is watching'), and a concrete observable effect ('turns its light green'). It also explains the session handoff purpose, which distinguishes it from the sibling tools ask_henry and search_sources.

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 gives explicit when-to-use guidance: 'Call this first if the person gave you a session code; otherwise it is optional.' It also names the alternatives (ask_henry and search_sources) and notes that they connect too, so an agent knows when this tool is not required.

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 mark the tool as read-only and non-destructive, lowering the bar. The description adds useful behavioral context beyond annotations: it returns passages with source links and explicitly states 'Fast; no model call,' which helps an agent set expectations about latency and behavior. No contradiction with annotations.

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 efficient sentences with no filler. The core action and result are front-loaded, and the parenthetical scope list adds useful specificity without bloat.

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 search tool with a read-only annotation, a simple schema, and no output schema, the description adequately conveys what the tool returns and the knowledge domain covered. It could be more complete by explicitly distinguishing itself from ask_henry, but the core calling context is covered.

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 67%: limit and session already have descriptions, while query has only length constraints. The description does not add meaning for the query parameter beyond the general knowledge-base scope, but this is acceptable because most parameters are already documented in the schema.

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: 'Search HenryKnows' knowledge base' and lists the covered content areas. It clearly conveys that the tool returns matching passages with source links for citation. It does not explicitly name or contrast the sibling tools, though 'no model call' hints at a difference from ask_henry.

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 gives clear context: use this when you need retrievable passages and source links to read and cite yourself, and it notes the tool is fast and does not make a model call. It does not provide explicit when-not-to-use guidance or name alternatives, but the intended use case is implied strongly enough.

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