AI Agent Shelter

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds two things the annotations cannot: the operation is 'Free' (no cost/charge), and the complete list of fields returned, which matters because no output schema exists.

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: cost and core action first, then the field enumeration. Efficient overall, though the long comma-joined field list reads as a run-on and could be trimmed if an output schema were added.

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 no output schema and no parameter descriptions, the description carries the burden and does so for return content (field enumeration) and cost. It stops short on the one thing an agent would still guess at: the slug format and what happens on an unknown slug.

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?

One required string parameter with 0% schema description coverage, so the schema gives the agent nothing. The description at least confirms the parameter's role ('by slug'), but adds no format, length, or lookup-failure guidance, leaving the identifier's semantics largely to inference.

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?

Specific verb (Read) + singular resource (one resident's full résumé) identified by slug, which cleanly distinguishes it from the plural sibling list_residents and the action sibling hire. The enumerated field list further pins down exactly what 'résumé' contains.

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 'before deciding whether to pay' states the decision context that selects this tool over hire, so the agent knows it is a pre-purchase inspection step. It never names the sibling hire explicitly or states any exclusion, so it falls just short of a 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 flag readOnly/idempotent/non-destructive, and the description usefully adds that the call itself is free, that no payment executes inside MCP, and that user approval of the amount is required before paying. This is real context beyond the structured hints, though it omits what happens if the endpoint is unavailable.

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 'Free to call', then the payload, then the payment caveat. Three tight clauses with no filler, though the MPP/Stripe jargon could be ordered more clearly.

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?

There is no output schema, and the description names the three returned items (endpoint, EUR price, payment-token command), which is adequate for a single-param tool. The main gap is the unresolved ambiguity with get_resident and slug validity.

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?

One required parameter ('slug') with 0% schema description coverage, so the description must compensate. It implies the slug identifies 'a resident' but never defines its format or what a valid slug looks like, leaving partial compensation only.

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 concrete outcome: retrieve a resident's paid HTTP 402 endpoint, current EUR price, and the exact payment-token command. The verb 'hire' is vague but the body clarifies it. It does not differentiate itself from the sibling get_resident, which could confuse selection.

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 gives useful workflow context ('Free to call', payment happens over HTTP not inside MCP, get user approval of the amount before paying), which implies when it fits. However it never contrasts with get_resident or states prerequisites (e.g., the resident must already be identified/willing).

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 cover read-only, idempotent, non-destructive, closed-world behavior, so the description only needs to add beyond that. It does: 'Free' discloses the cost profile and 'Prices may change' warns that returned EUR prices are volatile, which is genuinely new information. It stops short of pagination or rate-limit behavior.

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 cost signal, then a tight field inventory, then the freshness caveat. Dense but every clause earns its place; no filler.

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?

No output schema exists, and the description effectively substitutes for one by naming every returned field, plus it notes price volatility. The unexplained 'kind' filter is the only meaningful gap for a simple read-only 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?

Schema description coverage is 0% for the single 'kind' enum parameter, and the description never explains that 'kind' acts as a filter (it only lists 'kind' as a returned field, which is ambiguous). With low coverage the description was expected to compensate and it does not.

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 ('List') and resource ('every resident') and enumerates exactly what is returned (slug, kind, tagline, price, paid-call count, tools, hire URL, résumé page). This clearly separates it from the singular get_resident and the action tools hire/surrender.

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?

'Free' and 'read this before hiring' give a concrete usage context (inspect the resident catalogue before committing to a hire). However, no alternative is named explicitly — e.g. when to prefer get_resident for a single resident — and there are no exclusions.

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 only cover the safety hints (readOnly=false, destructive=false, idempotent=false, openWorld=false); the description adds real pipeline context: static checks precede behavioral screening, verified arrivals follow the owner's approval policy while suspicious ones stay held, and the return is slug/status/static report with no guarantee of publication. It does not mention auth needs, cost beyond 'free', or rate limits, so not a 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?

Four dense sentences, front-loaded with the operation and its pipeline, then the return semantics and prerequisite. No filler, though the metaphorical phrasing ('arrivals', 'screening') costs some clarity that plainer wording would not.

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 tool with 9 required params, a nested oneOf payload with three distinct submission kinds, low schema coverage, and no output schema, the description covers the process and return but says nothing about what shape of artifact to submit or how the kinds differ. An agent can call it, but not confidently.

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 only 30% across 10 parameters, yet the description never elaborates on name, tagline, story, creatorName, creatorContact, license, creatorSharePct, or the three-way 'spec' branch. It only gestures at agreementVersion and attestation; the oneOf spec variants (agent/mcp/mind) are entirely unexplained, so the description fails to compensate for the coverage gap.

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 frames the tool as a 'free declarative intake' that runs safety/screening steps and returns a saved slug/status, which tells an agent this is a write/submission operation distinct from the read-oriented siblings (get_resident, list_residents) and the transactional 'hire'. The verb is metaphorical ('surrender'/'arrivals') and the resource is never named plainly, so some inference is still required, but the operation is identifiable.

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 gives one prerequisite ('Read the surrender agreement and attest rights first') and implies when the tool applies (you have a spec to submit), but never states when NOT to use it or contrasts it with siblings such as hire. Guidance is implied rather than explicit.

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