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

With no annotations, the description carries the behavioral load and does disclose the basis of the determination (manufacturer-cited credential type), the output context (compliance index totals), and a caveat that this is documentation reading, not legal advice. It does not mention authentication, rate limits, or side effects, but those are minor for a read-only lookup.

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?

The purpose is front-loaded and the text is compact, with no empty filler. The first sentence is dense but earns its place by packing legal context and data source into one clause.

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 read-only lookup with no output schema, the description is nearly complete: it explains what is checked, where the slug comes from, and what context is returned. It could optionally clarify the return shape, but the index-totals mention already gives useful output context.

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. The description adds meaningful guidance by naming get_router_defaults as the source of the ssid.ai slug and implying its format, going beyond the schema's terse field description.

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 specific compliance check: whether a router model still ships a universal default password, tied to UK PSTI and EU CRA requirements. It distinguishes itself from the sibling get_router_defaults by telling the agent to retrieve the slug there first.

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 a clear prerequisite and source for the required slug, which is useful usage context. It does not explicitly state when not to use it or compare it to the other siblings, so it falls short of full alternatives guidance.

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 no annotations, the description carries the burden and does disclose notable behavior: results are cited to manufacturer documentation with the source URL, coverage is bounded to the 409-model ssid.ai directory, and the tool will report the absence of a default password rather than failing. It does not state error behavior for unknown models or any rate/auth constraints, so it falls short of 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?

It front-loads the returned data, then the input modes, then usage triggers and scope limits; every sentence contributes. It is dense and slightly run-on but contains no filler or repetition.

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 annotations, the description supplies the return payload contents, the sourcing guarantee, and the directory-size limit, which is enough for correct invocation. It stops short of describing failure behavior when the slug or brand/model is unmatched.

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 already 100%, so the baseline is 3, but the description adds real meaning by explaining the two alternative input modes ("Pass the ssid.ai slug, or brand plus model") — an exclusivity/combination rule the schema lists only as separate optional properties.

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 (router/gateway default credentials and factory-reset data) and enumerates exactly what is returned: gateway IP, admin username/password or its absence, credential type, and reset steps. It is clearly distinguishable from siblings like lookup_mac and check_router_compliance 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?

It gives explicit trigger conditions ("after lookup_mac identifies the vendor, or whenever a user asks for a router's default login, factory password, gateway address or reset procedure") and an explicit exclusion ("no listing or wildcard search"), plus the input-mode rule (slug or brand plus model). This is a full when/when-not/alternative disclosure.

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 no annotations, the description carries the full burden and does substantial work: it discloses the longest-prefix-first resolution against IEEE registries, that sub-blocks (MA-M/MA-S/IAB) win over the MA-L registrar, and that randomized addresses return vendor: null plus cidRegistrant with a concrete example (DA:A1:19 = Google). It omits error behavior for malformed MACs and whether lookups are local or networked, 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?

Front-loaded with the core purpose before diving into resolution mechanics and return fields. It is dense with useful specifics, though the enumeration of returned fields runs long for a single-sentence-per-idea structure; every clause still 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?

No output schema exists, so the description must describe returns, and it does so thoroughly: vendor, blockType, block start/end, OUI, kind, randomized flag, confidence, source registry file, plus the null-vendor/cidRegistrant special case. It lacks failure-mode coverage for invalid input, which is the main remaining gap.

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?

There is a single parameter with 100% schema description coverage ('A MAC address in any format, e.g. F4:F5:E8:11:22:33'), so the schema already does the work and the baseline is 3. The description adds no additional input-side semantics such as accepted separators or validation rules.

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 ('Identify the organisation behind a MAC address') plus a second distinct capability (detecting randomized/private addresses), which no sibling covers. The sibling tools (get_router_defaults, check_router_compliance) are clearly different concerns, and the description makes that separation explicit.

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 context for use (vendor identification, randomized-address detection) and explicitly routes a related need to a sibling: 'For the router's factory login, call get_router_defaults next.' It does not state exclusions or when this tool would be the wrong choice versus submit_correction, so it stops short of a full 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?

With no annotations, the description carries the full behavioral burden and does so well: it discloses that submissions are 'Queued for verification — never applied automatically' (not an immediate mutation), requires an official manufacturer source URL, and states the auth mechanism (SSID_API_KEY or Bearer token) plus its cost. These are exactly the traits an agent needs before invoking a write tool.

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-loads the action and then layers constraints in order of importance (source requirement, queue behavior, slug source, auth/cost). Dense but every sentence adds operational value; slightly packed for a single paragraph.

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 behavior, auth, cost, and source requirements for a 4-required-param submission tool with no annotations or output schema. It stops short of describing what the submission returns (e.g., a submission id) or post-verification handling, which would complete the picture.

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 baseline is 3, but the description adds real meaning: it lists the correctable fields, explains where the slug comes from (ssid.ai/routers/<slug>), and hardens the sourceUrl parameter with an official-source constraint beyond the schema's format:uri.

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 (propose a fix / submit a correction) and the exact resource fields it targets: gateway IP, username, password, credential type, and reset steps. It also implicitly distinguishes itself from the three read siblings by noting this is the paid write path while 'the three read tools stay free'.

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 clear conditions for use (you have a correction backed by a manufacturer source) and an explicit exclusion ('never an aggregator/forum'). It references the read tools only in the context of pricing rather than naming which sibling to use for reading, so the alternative routing 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.