sociahive

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so safety is covered structurally. The description adds genuinely useful non-annotated context: that it duplicates the <page_context> block (same data, wasted turn) and is redundant before mutations. It doesn't describe the return shape, but for a read-only probe that is minor.

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 core purpose, then the conditions of use, then the warning. Three tight sentences with zero filler; the redundancy warning earns its length by preventing a wasted turn.

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 parameterless, read-only probe with no output schema, the description covers what it returns, when to call it, and when not to. Nothing an agent needs to invoke it correctly is missing.

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 inherited baseline is 4. The description actually names the returned fields (route, entity type/id/name, selection), which compensates for the absent output schema, though that is return-value context rather than parameter guidance.

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+resource ('Returns what the user is looking at') and enumerates the exact payload — route, entity type/id/name, selection — so the agent knows precisely what this retrieves. It is clearly distinguishable from the sibling tools list_capabilities and whoami.

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?

Gives explicit trigger conditions ('Use ONLY when they ask what page they are on, or when <page_context> reads "(none …)"'), plus an explicit anti-pattern: never call it when page_context already names an entity, and never before editing/deleting that entity. When-to-use and when-not-to-use are both spelled out.

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 readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: results are per-user filtered by tier and flags, and, most importantly, it warns that this tool must not be used as an existence check — a usage hazard the annotations cannot express.

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 tight sentences: the return value first, then the only legitimate trigger, then the anti-pattern. Every sentence earns its place and the most failure-prone guidance (don't use as preflight) is stated plainly rather than buried.

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, output-schema-less listing tool, the description covers what returns, how it is scoped, and the single misuse case that would otherwise cause agents to waste calls. Nothing further is needed to 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 the baseline is 4. The description correctly adds no parameter detail because there is none to add, and the 'filtered by tier + flags' note clarifies that the output is implicitly scoped by the calling user rather than by an argument.

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 ('Returns the list of tools available to this user') and adds the scoping detail '(filtered by tier + flags)', so an agent knows exactly what comes back. It does not name or contrast itself with the siblings whoami or current_page_context, so it stops short of a 5.

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 gives both the trigger ('Use ONLY when the user asks "what can you do?"') and the exclusion ('NOT a preflight — never call it to check whether a capability exists before acting'), plus the alternative behavior ('just call the one that fits'). This is a textbook when/when-not/alternative statement.

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 safety is covered. The description adds genuinely new behavioral context: it is not to be used as a preflight and the server enforces tier regardless of any check. It stops short of describing response shape or freshness, so not a full 5.

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 waste, with the return contents front-loaded and the misuse warning immediately after. Every clause 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 zero-parameter read tool with no output schema, the description already enumerates the returned fields and rules out the main misuse pattern, so an agent has everything needed to decide and call 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 the baseline is 4; there is nothing parameter-related the description could clarify. The mention of 'currently selected connected account' hints at ambient state but does not map to any 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?

States a specific verb and enumerates exactly what is returned (identity, tier, surface, selected connected account), which cleanly separates it from siblings like current_page_context and list_capabilities. No ambiguity about the resource being queried.

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?

Gives an explicit positive trigger set (user asks who they are, their plan, or selected account) and an explicit negative case ('NOT a preflight — never call it to check the account or tier before a write'). This is exactly the when/when-not guidance that prevents wasted calls.

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