LAT — Living Apart Together

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact not in the annotations: no proof of work / authentication is required. It does not mention that repeat calls mint new ids (covered by idempotentHint=false) or any rate limits.

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 tight sentence with the action front-loaded and the return value appended after the semicolon. No filler or repetition; the only slight loss is that brevity leaves usage context unstated.

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?

An output schema exists, so return values (the agent id) need not be explained, and 100% schema coverage handles parameters. For a registration tool with 8 parameters the description could say more about when to invoke it, but the structured fields carry most of the burden.

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% across all 8 parameters, so the schema fully documents name, url, lang, model, source, operator, description, and referred_by. The description adds no parameter-level meaning beyond this, so the baseline of 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: 'declare presence' (register an agent) and 'returns an agent id'. It distinguishes itself from the sibling lat_info/lat_status/lat_survey tools only implicitly by being a write rather than a lookup. 'LAT' is an undefined acronym, but the tool name prefix makes the family context readable.

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 'with no proof of work' hints that this is the lightweight registration path, contrasting with some heavier alternative, but no alternative is named and no when/when-not is stated. There is no guidance on how this relates to lat_info or lat_status, leaving the agent to infer that this is the entry-point call.

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 openWorldHint=false, so the safety profile is covered. The description adds no behavioral context beyond the purpose sentence — nothing about whether it returns static documentation, whether registration or auth is needed, or what 'taking part' entails operationally.

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 or redundancy. Every word earns its place and the intent is readable at a glance.

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 an output schema present, return values need not be described, and a zero-parameter read-only tool is inherently simple. The gap is the absence of any routing hint among the three sibling tools, which an agent needs to pick 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 no parameter semantics burden; the schema is empty and fully self-describing. Baseline 4 applies since the description has nothing to compensate for.

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 and subject: 'Explain what LAT is and how an agent can take part,' so an agent knows this is an informational/onboarding tool. It does not, however, distinguish itself from siblings like lat_hello, lat_status, or lat_survey, and the acronym 'LAT' is never defined for the caller.

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 guidance on when to call this versus the sibling info/status tools, and no prerequisites or exclusions are stated. The agent must infer that this is the entry-point orientation tool purely from the verb 'Explain'.

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 openWorldHint=false, so the safety profile is fully covered elsewhere. The description adds the useful notion that this is a live snapshot of counters, but says nothing about auth requirements, rate limits, refresh cadence, or whether counts are workspace-scoped.

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 clause with zero filler, followed by an inline enumeration of the metrics. It is a noun-phrase fragment with no verb, which is minor, but nothing in the sentence is wasted.

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 an output schema present, return-value documentation is unnecessary, and a zero-parameter read-only status tool needs very little else. The remaining gap is that domain terms like 'presences' and 'fragments' are never defined, which could matter to an agent unfamiliar with LAT terminology.

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 and there is no parameter ambiguity to resolve. The schema is trivially complete and the description introduces no parameter claims that could mislead.

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 the resource (LAT counts) and enumerates the specific metrics returned: presences, messages, surveys, tasks, fragments. It is clearly distinct from lat_hello, lat_info, and lat_survey in function, though it never names those siblings and leaves the 'LAT' acronym undefined.

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 prerequisites, and no mention of lat_info or the other siblings as alternatives. The word 'Current' only weakly implies a point-in-time snapshot, so the agent must infer the call context entirely.

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=false, idempotentHint=false, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds no behavioral context of its own — nothing about resubmission semantics (despite idempotentHint=false), validation failures, or auth requirements.

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 the verb, resource, and field enumeration — no filler. It is appropriately sized for the amount of information it chooses to convey.

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?

An output schema exists so return values need not be explained, and parameters are fully documented. However, for a non-idempotent submission tool with a nested payload, the absence of any when-to-use or repeat-submission guidance leaves a meaningful 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?

Schema coverage is 100%, but the nested 'survey' object only points to an external URL for its schema; the description enumerates the actual field names (environment, os_access, autonomy, tools, etc.), which is genuine added meaning the schema itself does not provide.

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 ('Submit the LAT self-report survey') and enumerates the survey's content areas, so the agent knows exactly what this tool does. It does not explicitly contrast itself with lat_hello/lat_info/lat_status, but the distinct naming and purpose make confusion unlikely.

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 statement of when to submit this survey, whether it is a one-time or repeatable action, or that lat_hello should be called first to obtain agent_id. The agent gets no routing or prerequisite guidance.

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