HenryKnows

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false. The description adds useful behavioral context beyond those fields: answers take 10–40 seconds, nothing is stored, and the answer is cited. It does not mention rate limits or authentication, but covers the key latency and privacy expectations.

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 three short sentences and is front-loaded with the purpose. Every sentence adds useful information: scope, usage guidance, and latency/privacy expectations.

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 simple two-parameter question-answering tool with rich annotations and full schema coverage, the description is largely complete. It explains what the tool returns at a high level (a cited answer) and sets expectations for latency and storage, though it does not discuss answer formatting or audience behavior.

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 both parameters are already well documented in the schema. The description adds only the instruction to ask in the person's own terms and avoid identifiers, which partially overlaps the schema's question description and does not explain the audience enum.

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: ask a question about F-1/J-1 immigration, SEVIS, OPT, CPT, and get a cited answer. It is clear what the tool does, though it does not explicitly distinguish itself from the sibling tools connect, search_sources, or share_to_page.

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 clearly scopes usage to immigration and student-status questions and adds a practical instruction to ask in the person's own terms without identifiers. It does not state when not to use the tool or name alternatives such as search_sources, so it stops short of full alternative routing.

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?

Goes well beyond the annotations: it discloses that the call creates a session or links the supplied one, returns the session and the page's watch link, that a new session is started on every call without a code, and that nothing is deleted. The non-idempotency hinted by idempotentHint=false is spelled out in concrete terms.

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?

Front-loaded with the action and its payoff, and every clause carries information. Slightly dense, and 'nothing is deleted' partially duplicates destructiveHint=false, but it costs little and reassures on a mutation.

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 one optional parameter, no output schema and only sparse annotations, the description covers the action, the gating condition, the side effects, and the return values (session plus watch link). An agent has enough to call it correctly and to know what comes back.

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% and the single property already documents the 64-hex session code and that omitting it starts a new session. The description reinforces the omit-behavior ('a new session starts each time it is called without a code') but adds no format or validation detail beyond the schema, so baseline 3 applies.

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 and resource ('Connect to the HenryKnows page the person is watching') plus the concrete outcome ('get the session for share_to_page'), which also positions it relative to the share_to_page sibling. The parenthetical 'its light turns green' makes the effect observable.

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 gates usage: 'Only for people who gave you a session code or asked to follow along on a page.' That is a clear when-to-use and an implicit when-not-to-use. It stops short of naming an alternative tool (e.g. ask_henry) for the case where no page is involved, so it is not a full 5.

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, idempotentHint, and destructiveHint=false, so 'Read-only: nothing is stored' largely restates structured data. The genuinely additive disclosure is 'Fast; no model call', which tells the agent there is no LLM latency or cost — useful, but a single trait. Nothing is said about result ranking, empty-result behavior, or passage truncation.

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 filler. The content scope and return value lead, and the operational traits ('Fast; no model call', 'nothing is stored') are packed into the trailing fragments rather than a separate paragraph.

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 two-parameter read-only retrieval tool with rich annotations and no output schema, the description covers what it searches, what it returns, and its cost profile — enough to call it correctly. The remaining gap is query formulation guidance for the undocumented required parameter, which is the one thing an agent could get wrong.

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 only 50%: 'limit' is documented (default 6, range 1–10) in the schema, but 'query' has no description anywhere. The tool description does not clarify whether query is natural language, keywords, or a citation fragment, nor does it mention the limit parameter at all, so it fails to compensate for the coverage gap on the one required parameter.

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 gives a specific verb (search) and resource (HenryKnows' knowledge base) and even enumerates the content domains — regulations, SEVP/USCIS guidance, Federal Register rules — plus what the agent gets back (matching passages with source links). It implicitly separates itself from ask_henry via 'no model call', but never names the sibling explicitly, so the differentiation is inferred rather than stated.

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 clause 'so you can read and cite the text yourself' plus 'Fast; no model call' clearly signals the use case: raw, citable passages rather than a synthesized answer from ask_henry. It stops short of an explicit when-not rule (e.g., 'use ask_henry instead when you want a summarized answer'), so the routing decision is left partly 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?

Adds meaningful context beyond the annotations: appends exactly one entry to the page's thread, keeps it for 24 hours, and changes nothing else. This is a good disclosure for a mutation with destructiveHint=false, though it does not describe repeated-call behavior despite idempotentHint=false.

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 tight sentences with the action and scope front-loaded, followed by the prerequisite and side effects. Every sentence carries distinct 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?

Covers purpose, prerequisite, retention, and side effects, which is strong for a five-parameter mutation with no output schema. It leaves minor gaps around repeated invocations and the audience parameter, but an agent has enough 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 80%, so the schema already documents the answer, session, sources, and question parameters. The description clarifies the answer-or-search shape but does not add meaning for the undocumented audience parameter or deeper source structure, so baseline 3 is appropriate.

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 and resource: adding a question/answer or search/passages exchange to the connected HenryKnows page thread. It is clearly distinct from ask_henry, connect, and search_sources, which respectively produce answers, establish sessions, 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?

Explicitly restricts usage to 'people who connected a page,' which links the tool to the connect sibling as a prerequisite. It implies this is a follow-up step after an exchange, though it does not explicitly contrast with ask_henry or say when not to share.

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