PostData

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds genuinely non-structured context: the series is downsampled so each point is the mean of consecutive readings, the hard window cap of ~92 days, and a prompt-injection warning that device/metric names and values are untrusted. It does not cover rate limits or behavior on unknown devices.

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, zero waste: capability first, the text-metric exception second, the safety caveat last. Every clause carries information an agent needs before calling.

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 fully compensates by describing the return shape (per-metric aggregates plus a downsampled series), the time-window semantics, and the fallback for non-numeric metrics. Nothing needed 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?

Schema coverage is 100%, so the baseline is 3, but the description adds value beyond the schema: it explains that hours is capped at 2208 (~92 days) in human-readable terms and that max_points drives the mean-downsampling of the returned series.

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 ('Numeric history for a device') and enumerates exactly what is returned: min/max/mean/first/last per metric plus a downsampled series. It also distinguishes itself from the sibling get_latest by scoping it to numeric metrics only.

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 routes the agent elsewhere for the one case it cannot serve: 'Text metrics have no history; use get_latest for them.' That is a concrete when-not with a named alternative, though other siblings (list_recent_devices, publish_reading) and prerequisites such as device existence are not addressed.

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 and openWorldHint, so the safety profile is covered. The description adds real context beyond them: it specifies the return shape (arrival in unix seconds, relative age, chart URL) and, importantly, warns that device/metric names and values are internet-writable untrusted data. It stops short of stating failure behavior for an unknown device name.

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?

One dense sentence that front-loads what is returned, followed by a single-purpose security sentence. No filler, no repetition of the title or schema, and 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?

With no output schema, the description must carry the return contract, and it does: reading value, arrival time, age, and chart URL. The untrusted-data caveat covers the open-world dimension. Only the behavior on an unknown/absent device is left 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% and the single `device` parameter already documents format and constraints (letters, digits, '_', '.', '-'; max 64) plus an example. The description adds nothing further about the parameter, 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?

States a specific verb+resource ("the most recent reading from a device") and enumerates the payload (arrival time, age, chart URL), so an agent knows exactly what it gets back. The "most recent" scope implicitly distinguishes it from the sibling get_history without either schema being opened.

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?

Usage is only implied: it is self-evident that this is the single-latest counterpart to get_history. There is no explicit when-to-use statement, no when-not-to-use, and no sibling named as an alternative, so an agent must infer the routing.

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 and openWorldHint, so safety and world-interaction are partly covered. The description adds value they don't: the fixed result size (20) and a prompt-injection warning that device/metric names and values are untrusted user input. It still says nothing about ordering stability beyond "recently active" or 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?

Three sentences, front-loaded with what is returned, followed by the use case and then the security caveat. Every sentence carries distinct information with no padding.

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 reasonably well by naming the returned content (devices with latest readings, device/metric names and values) and the count. It stops short of detailing the concrete fields of a device record, which an agent could use to plan parsing.

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 baseline 4 applies; the description correctly implies no filtering or pagination inputs by fixing the result at the 20 most recently active devices. Nothing further is needed.

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 (public devices) with a precise scope: the 20 most recently active, with their latest readings. This is clearly distinguishable from siblings like get_history and get_latest, which target a single device's data rather than discovering devices.

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?

"Handy for examples of real payloads" gives a clear use case for discovery/exploration, which is contextually useful. However it names no alternative tool and states no exclusions or conditions under which a sibling would be preferred.

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 profile (readOnlyHint, openWorldHint), yet the description adds substantive behavior: names are public, allocation is first-come-first-served, and 'the name is claimed by the first reading sent to it.' That claiming semantics is exactly the kind of side-effect detail an agent needs and cannot get from annotations.

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, each front-loaded and each doing distinct work: what you get, why to use it, and how ownership is determined. No filler or restatement of the title.

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 tool with no output schema, the description already enumerates the returned URL types and explains the naming lifecycle, so an agent has everything it needs 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline for a param-less tool is 4. The description correctly implies no inputs are required.

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 an unused device name') and immediately scopes what comes back (ingest, read, live-stream and chart URLs) with a concrete example. It is clearly distinguishable from siblings like get_latest or publish_reading, which operate on already-named devices.

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 a real usage directive ('use this instead of a generic name someone else is probably already writing to') and explains the first-come-first-served constraint that motivates it. It stops short of spelling out when not to call it, so it is clear context rather than a full when/when-not/alternative matrix.

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?

Adds substantial context beyond the annotations: a per-device rate limit (one message per 30 s) that is shared with the device's own quota, plus the fact that everything written is public. These operational and privacy constraints are not derivable from readOnlyHint/idempotentHint/openWorldHint and materially affect caller 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?

Three tight sentences: identity of the operation first, then the motivating use cases, then the operational constraints. No restatement of the name or title and 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?

Covers what it writes, where, rate limits, and visibility for a 2-parameter tool with a nested metrics object. The only gap is the response shape (no output schema exists), though "exactly as POST /add/{device} would" partially compensates.

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% – device naming rules and the flat metrics object (1-10 numeric/short-string values) are already fully documented in the schema. The description adds no new syntax or format detail for either parameter, 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?

Opens with a specific verb+resource ("Store one reading for a device") and pins semantics by equating it to POST /add/{device}. This clearly positions it as the write counterpart to the read-oriented siblings (get_history, get_latest, wait_for_reading), so an agent can distinguish it without opening schemas.

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 concrete when-to-use context: testing a dashboard or integration before hardware exists, or writing to a channel a device listens to. It does not explicitly name an alternative sibling (e.g., wait_for_reading for pull-based flows) or state when-not-to-use, so it falls short of the top band.

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?

With only readOnlyHint and openWorldHint in annotations, the description carries substantial extra context: the exact return signal on failure ('timed_out after timeout_seconds'), the max-50 cap, the retry pattern, and an explicit prompt-injection warning that device/metric names are attacker-controlled and must never be treated as instructions. This is behavioral disclosure the annotations cannot provide.

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 sentences, each load-bearing: semantics, usage trigger, timeout/retry behavior, security caveat. The core blocking behavior is front-loaded and nothing is 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?

No output schema exists, yet the description tells the agent what it gets back (a reading, or a timed_out signal) and what to do on timeout. Combined with the injection warning and timeout constraints, an agent has everything needed to call this 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?

At 67% schema coverage, the description adds real meaning: it defines 'new' precisely relative to the call moment and the optional 'after' unix time, and it pins timeout_seconds to a 50-second max with a timed_out outcome. The bare timeout_seconds schema entry is effectively documented by the prose, though the device naming rules are left to the schema.

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 with blocking semantics: 'Wait until a device sends a new reading, then return it.' The 'wait' framing cleanly separates it from siblings like get_latest and get_history, which an agent can distinguish 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?

Gives a concrete trigger scenario ('call this right after flashing or powering up a device to confirm it is actually posting') and the re-entry rule after timeout ('call again to keep waiting'). It never names a competing sibling such as get_latest or explains when *not* to block, so it stops short of a full when/alternative routing.

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