Flathive

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description adds genuinely new behavior: it discloses the fields returned and, more importantly, that no interactive widget exists and contact/gallery/location are impossible through this tool. That 'negative capability' disclosure is the kind of context annotations cannot carry. Auth requirements, rate limits, and pagination are not mentioned, but for a read-only lookup that is a minor gap.

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 operation before the usage caveats, and no filler. The second sentence is long and heavily em-dashed, packing four distinct constraints into one breath, which slightly hurts scanability but every clause carries information.

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 the field list is arguably redundant, but the description still covers what an agent needs: what the tool returns, what it cannot do, and what to tell the user. The one omission is how to source an easyId, which matters for a tool that requires one. Overall adequate for a two-parameter read-only lookup.

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%, and the schema already documents easy_id with an example ("P000204") and country_type as required for building the public URL. The description's only addition is the 'starts with P' prefix rule, which is marginal against the schema's example. Baseline 3 applies when the schema does the heavy lifting.

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 ("Get a summary of one Flathive property listing") plus the identifier type and format ("public easyId (starts with \"P\")"), and enumerates what comes back: bio, features, tags, photo URLs. That single-listing-by-id scope distinguishes it cleanly from the sibling search_properties.

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 downstream handling instructions ("always surface the returned url and tell the user to open it on Flathive") and states what the tool cannot do (gallery, exact location, messaging). It does not tell the agent where to obtain an easyId in the first place, i.e. it never names search_properties as the discovery path, so the alternative-tool routing is implied rather than stated.

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 establish read-only, idempotent, non-destructive, closed-world behavior, and the description adds genuinely new context: results are limited to 'published' listings, coordinates are deliberately jittered (~100m) for landlord privacy, and exact addresses are shared only after contact with consent. That privacy caveat directly shapes how an agent should present results and is not derivable from any structured field.

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 sentences, each doing distinct work: purpose first, then the blocking prerequisite, then the output caveat. Nothing is repeated and the most important constraints are front-loaded.

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 14-parameter search tool with an output schema already covering return values, the description supplies exactly the missing pieces an agent needs: the mandatory country prerequisite and the jittered-coordinate privacy caveat. No call-critical information is absent.

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 high at 79%, so the schema already documents limit caps, rent/stay bounds, and the enum values. The description reinforces the required/conditional nature of country_type (ask the user or infer it) but adds no syntax or format detail for the location or filter parameters, so the baseline 3 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?

The description names a specific verb and resource — 'Search published Flathive room/property listings' — plus the scoping dimensions ('by location and filters'). It is clearly distinct from a details-fetch tool, though it never names the sibling get_property_details explicitly, so an agent must infer the split.

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?

Strong prerequisite guidance: it states country_type is required and instructs the agent to ask the user or infer the country from a named suburb/city before calling. It does not state when to prefer this over get_property_details, leaving that transition to inference.

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