Ashraf Gents Hostel, Kalamassery

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

Annotations declare readOnlyHint and openWorldHint, and the description adds genuine behavioral context beyond them: the artifact produced is a message, the user must send it, and confirmation comes from the hostel. It also states a subject restriction ('Men only') absent from the schema. Return content/format is not described, keeping it below 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?

Three short sentences, front-loaded with what the tool does, followed by the most important negative constraint and the eligibility restriction. 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?

Given no output schema and a deep non-booking constraint, the description covers purpose, boundary, and eligibility well. The remaining gap is parameter meaning for a 6-param tool, which is only partially handled by the schema.

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?

Six parameters with only 50% schema description coverage, and the description explains none of them. Semantics for length (nights vs months), purpose, and guests must be inferred entirely from the schema, and 'Men only' is not mapped to any parameter.

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 ('prepares a WhatsApp message to Ashraf Gents Hostel asking whether a bed is free') and immediately disambiguates scope by ruling out booking. An agent can distinguish this from get_guide, get_hostel_facts, and search_guides without opening any schema.

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 states what the tool does NOT do ('does NOT book or reserve anything; the user must send the message and the hostel confirms'), which defines the boundary against a hypothetical booking sibling. It does not name any actual sibling alternative, so it falls 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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds the output shape (Markdown plus sources and citation), but says nothing about behavior on an invalid or missing slug, or whether the guide content is cached/versioned.

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, front-loaded with what is returned and followed by the one usage instruction. Nothing is redundant or 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?

For a simple single-parameter read tool with no output schema, the description covers the resource, the return format, and the source of the identifier. An agent has everything needed to call 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?

Schema coverage is 100% and the single parameter already documents both accepted forms ('slug or its full URL'). The description's mention of the slug/URL adds no syntax or format detail beyond what the schema states.

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 specific resource ('one guide') and its return format ('Full text ... as Markdown, with its sources and citation'), which distinguishes it from the plural search_guides sibling. It is clear and concrete, though it describes the output more than it states a retrieval verb.

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?

'Pass the slug or URL from search_guides' establishes the prerequisite and effectively routes the agent to search_guides for discovery. There is no explicit when-not guidance, but the usage condition is unambiguous for a simple one-parameter lookup.

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 safe, static read profile is covered structurally. The word 'canonical' usefully signals an authoritative reference rather than live data, but the description adds no detail on freshness, rate limits, or return shape beyond that.

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 that leads with 'Canonical facts' and then lists contents. Every item earns its place by telling the agent what queries it can answer; it is slightly list-like but not padded.

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 params, no output schema, and annotations covering the read-only profile, the description's content enumeration is sufficient for an agent to call it and anticipate the result. The only missing piece is contrast with the sibling lookup tools.

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 and the baseline of 4 applies. The empty schema is consistent with an all-facts-in-one-call design.

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 specific resource (canonical facts about Ashraf Gents Hostel) and enumerates the exact content returned: address, phone/WhatsApp, rooms, rates, rules, map position. An agent can immediately tell what it retrieves, though it draws no boundary against siblings like check_availability or nearby_places.

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 states what is returned but never says when to call this versus check_availability, nearby_places, or get_guide. No prerequisites, triggers, or exclusions are given, leaving the routing decision entirely to inference.

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 usefully adds that distances are straight-line rather than routed, that the radius is roughly 1.3 km, and attributes the OSM data source — but it says nothing about result ordering, empty-result behavior, or how the default radius is applied.

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 leads with the core output and scope, followed by the attribution line. The long parenthetical category list is dense but informative; nothing is wasted, though it could be trimmed since the schema repeats the categories.

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, the description does the work of explaining what comes back (places plus landmark distances), which is the key missing piece. It is close to complete for a read-only, zero-required-parameter tool; only default-radius and result-ordering behavior are unstated.

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%, so the schema already documents all three parameters including the category list and landmark examples. The description merely restates the same categories and landmark names, adding no syntax, defaults, or interaction rules beyond what the schema provides.

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 precisely what the tool returns — named places within ~1.3 km plus straight-line distances to named landmarks — which is a specific resource with a stated scope. It is clearly distinct from the sibling tools (availability, guides, hostel facts), though it never explicitly names or contrasts them.

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 get_guide or get_hostel_facts, nor any note on prerequisites or typical query patterns. The content is described, but the conditions for selecting this tool are left entirely to inference.

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 declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description usefully discloses the return payload (titles, URLs, summaries, key facts, citation), which matters because no output schema exists, and the local-guides framing is consistent with the closed-world annotation. No contradiction.

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, front-loaded with the core action and scope, and the parenthetical enumeration earns its length by telling the agent what content exists. The topic list is dense but not padded.

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 read-only search tool with no output schema, the description covers what is searched, the domain scope, and what is returned. Remaining details (limit default of 5, max 10, category filtering) are already in the schema, so nothing an agent needs to call 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?

Schema description coverage is 67%: query and category are documented in the schema itself (including examples and a topic list), while limit has only a default/max. The description adds no meaning beyond the schema for any parameter, 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 ('Search') and resource ('the hostel's guides') and pins down the corpus with a concrete topic list (CUSAT, NUALS, RCC/CCRC, transport, food, festivals). It does not explicitly distinguish itself from the sibling get_guide, so an agent must infer search-vs-fetch from the names alone.

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 topic enumeration implies when the tool is useful (local questions about colleges, transport, services), but there is no explicit when-to-use statement, no exclusions, and no routing against siblings like get_guide or nearby_places. Usage is only implied.

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