Major Labs

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

With no annotations, the description carries the full burden, and it does disclose useful traits: the data is dated and traced to primary sources, which signals provenance and historical coverage. However, it says nothing about return format, size, update cadence, or whether it is a static snapshot versus a live feed. Adequate for a zero-param read tool but with clear gaps.

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 with the scope front-loaded ('Every announced framework, protocol, standard, and regulation') followed by the qualifiers. No filler, no repetition of the title.

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 read tool with no output schema and no annotations, the description conveys what the returned dataset contains and its sourcing discipline, which is enough to call it correctly. It stops short of describing freshness or format, but those are minor for a reference-listing tool.

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 the baseline is 4. There is nothing for the description to clarify beyond confirming that the result is a broad, unfiltered enumeration ('Every announced framework...'), which it does.

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 resource — a dated, source-traced registry of frameworks, protocols, standards, and regulations for AI agent identity, delegation, and KYA — which is clearly distinct from the sibling tools (ecosystem stats, trust index, incidents). The implied verb (retrieve/list) is not stated explicitly, but the content is unambiguous. It loses a point only for not naming siblings 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?

There is no when-to-use guidance, no conditions, and no named alternatives among the siblings. Usage must be inferred purely from the resource description. An agent cannot tell from the text whether this is the right tool for a standards-lookup question versus a stats or incidents question.

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 it does disclose that the data is a 'firsthand, read-only measurement' (i.e., original, not derived/cached, and non-mutating). It omits freshness/staleness semantics for the weekly cadence, auth requirements, and response shape, so the disclosure is partial.

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 compact sentences, front-loaded with the resource and then the returned dimensions. Near-optimal for the size, with only mild padding from the 'Firsthand, read-only measurement' clause.

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-param, no-output-schema aggregate query, the description covers the resource, the categories of data returned, and the read-only nature of the call. An agent has enough to select and invoke 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-argument tool 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?

Names a specific resource (aggregate statistics of the MCP server ecosystem) and enumerates the content categories it returns: census size, activity, transport/language breakdowns, and security/identity aggregates. This distinguishes it reasonably from per-entity siblings like get_agent_identity_tracker and get_trust_index, though it never explicitly states the contrast.

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?

'Major Labs weekly sweep' signals a periodically refreshed, aggregate dataset, which implies when to prefer it over entity-level tools. However, there is no explicit when-to-use statement, no exclusions, and no named alternative among the siblings.

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 behavioral burden. It does add useful semantics beyond the schema by defining what a change event represents (a lab edited its safety commitments), but it omits whether the call is read-only, how snapshots are ordered or paginated, history depth, and the return format.

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 zero padding; the data description is front-loaded and the second sentence earns its place by decoding the changelog semantics an agent would otherwise have to guess.

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-argument tool this is close to adequate, but with no output schema and no annotations the description should say more about the shape of the returned snapshots/diffs (format, ordering, whether full history or latest) so an agent knows what it will actually receive.

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 per the rubric the baseline is 4. There is nothing for the description to compensate for, and no parameter-level misdirection.

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 conveys the resource: dated, hashed snapshots of frontier labs' safety frameworks plus diffs, with a definition of what a change event means. It is specific about content, but uses no explicit verb (e.g. 'retrieve') and does nothing to distinguish it from siblings like get_trust_index or list_incidents.

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?

There is no explicit when-to-use statement, no prerequisites, and no named alternatives among the four sibling tools. An agent could infer it is for tracking safety-framework edits, but nothing tells it when this tool is the right choice over get_trust_index or list_incidents.

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?

No annotations are provided, so the description carries the full behavioral burden. It states the output is a composite score with pillar breakdowns and methodology version, which is useful, but doesn't specify refresh cadence, data sources, historical availability, or what 'methodology version' means for interpretation. For a data-read tool with no annotations, this is incomplete.

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 well-structured sentence front-loads the key purpose (weekly composite score) and then details its components. It is efficient and information-dense without redundancy, though slightly long for a zero-parameter getter.

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?

Given no output schema, no annotations, and zero parameters, the description must convey the return value's shape and the tool's operational context. It describes the output as a composite score with pillar numbers and methodology version, but omits cadence details, freshness guarantees, and how to interpret the score—gaps that matter for a monitoring tool.

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 has zero parameters, so there are no parameter semantics to document. The baseline score is 4 per the rules (0 params = baseline 4), and the description appropriately does not waste space on non-existent parameters.

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 (returns/describes) and resource (the weekly Agent Trust Index, a composite 0-100 score), and details its composition (code-safety, identity, supply-chain pillars). This clearly distinguishes it from data-fetching siblings like get_mcp_ecosystem_stats which covers ecosystem metrics, not a fused trust score.

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 implies usage (retrieve the current trust index) but doesn't explicitly state when to use this vs alternatives like get_threshold_watch or get_agent_identity_tracker. No exclusions or prerequisites are mentioned.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states that every claim has published inclusion criteria and sources, which adds some data-quality context, but it omits basic operational traits such as whether the tool is read-only, paginated, or returns a static dataset.

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 a single, front-loaded sentence that efficiently conveys the resource's scope and key attributes without any filler or repetition. Every part of the 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 simple, zero-parameter list tool with no annotations or output schema, the description adequately explains what the records contain and their sourcing. It could be slightly more explicit about returning a list of records, but the tool name "list_incidents" compensates for that minor gap.

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 has zero parameters, so the baseline score is 4. The description does not discuss parameters (there are none), and no additional param semantics are needed.

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 identifies the resource as a record of frontier AI control incidents, listing specific incident types (containment escapes, unsanctioned live-system actions, etc.) and distinguishing it from sibling tools that cover trackers, stats, watch, and index. However, it lacks an explicit action verb like 'list' or 'retrieve' and relies on the tool name to convey that it returns a list.

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 provides no guidance on when or why to use this tool versus alternatives. It does not mention any conditions, prerequisites, or exclusions, leaving the agent with no usage context beyond the content itself.

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