AIS Gateway — the campus front desk for AIS MCP buildings

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

No annotations are provided, so the description carries the entire behavioral burden. It discloses one genuine trait — the call is free — but says nothing about permission requirements, response shape, or whether the content is static vs. live pricing, which is significant given the tool advertises prices that could change.

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 sentence, front-loaded with the most decision-relevant token ('FREE') and then a compact enumeration of contents. The parenthetical list is dense but every item maps to real advertised content, so little is wasted; slightly heavier than needed for the amount of guidance it gives.

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 zero-parameter, no-output-schema informational tool, the description is sufficient: an agent knows what it will learn and that it costs nothing. The remaining gap is the lack of differentiation from how_to_pay and list_buildings, which leaves some ambiguity about call ordering.

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 tool takes zero parameters, so there is no parameter semantics to document and the baseline of 4 applies. The description correctly implies a parameterless catalog call rather than suggesting any filtering input.

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?

Names a concrete resource (the AIS front desk / catalog) and enumerates the content: tested code libraries, CVE intelligence, Agent Flight Recorder, buildings, prices, x402 purchasing. That is specific enough to distinguish it from a generic help tool, but the overlap with siblings is unresolved — 'which building serves what' duplicates list_buildings and 'how agents can buy over x402' duplicates how_to_pay.

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 leading 'FREE' hints that cost is not a barrier to calling it, but there is no explicit when-to-use guidance and no routing to or away from the two siblings. An agent cannot tell from this text whether to read about_aislabs first or go straight to list_buildings/how_to_pay.

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?

With no annotations, the description carries the full burden and does add real behavioral context: it states the call is FREE, gives the Authorization: Bearer header for key-based access, and enumerates concrete prices/terms for each paid option. It stops short of describing what the response contains, but for a zero-parameter informational tool the disclosure is substantial.

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 dense sentence, front-loaded with the key fact 'FREE.' Pricing is emitted compactly via em-dash asides. The embedded price list is bulky but is essentially the payload of the tool, so it earns most of its space.

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?

Zero parameters and no output schema mean the bar is low. The description covers both payment routes with prices and terms, which is nearly everything an agent needs before calling. It could note that the response returns full instructions, but the coverage is close to sufficient.

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 schema has zero parameters, so the baseline is 4. The description introduces no parameters and needs none; there is nothing for it to clarify beyond what the empty schema already conveys.

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 names a clear topic — the two payment doors for the API (Gateway key vs per-call x402) — and the topic is distinct from siblings about_aislabs and list_buildings. However, it never states what the tool actually does or returns (e.g. 'returns payment instructions / pricing'), reading as a content dump rather than a stated verb+resource.

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?

'When to use each' refers to choosing between the two payment methods, not to when an agent should call this tool versus its siblings. There is no guidance on the trigger condition for invoking how_to_pay, so usage must be inferred.

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?

With no annotations, the description carries full behavioral burden. It usefully flags 'FREE' (cost) and enumerates the payload contents including key scope and key cost, but says nothing about authentication requirements, output format, or pagination for a potentially broad directory.

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 most decision-relevant token ('FREE') followed by a single dense sentence and a routing hint. No wasted sentences, though the middle clause is list-heavy.

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 no-parameter, no-output-schema discovery tool, the description enumerates what comes back (URL, tools, prices, free tier, key scope, key costs) well enough for an agent to know it should call this first. Only the lack of auth/format detail keeps it from a 5.

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?

Zero parameters, so the baseline is 4. There is nothing for the description to disambiguate, and it does not need to.

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 the resource precisely: a directory of every AIS MCP building with URL, tools, prices, free tier and key scope. This clearly separates it from siblings like about_aislabs and how_to_pay, though the verb is implicit (no explicit 'list'/'retrieve').

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?

'Start here.' gives a clear implied entry-point cue, but it never names the sibling tools or states when this should be used instead of about_aislabs or how_to_pay. Usage is implied rather than specified.

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