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

With no annotations, the description carries the full burden of behavioral disclosure. It implies a mutation ('register'), but does not state whether an existing site is overwritten, what permissions or auth are required, how secrets are handled, or what side effects occur.

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 single sentence is front-loaded and has no wasted words, but it is severely under-specified for a 9-parameter mutation tool. Conciseness here comes at the cost of necessary detail.

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 the complexity of a 9-parameter mutation with no annotations, no output schema, and zero schema description coverage, a one-sentence description is not complete enough. An agent lacks the context needed to invoke this tool 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 schema has 9 parameters with 0% description coverage, so the description must compensate. It adds almost nothing beyond echoing 'site', 'profile', and 'login identity', leaving parameters like check, secret, window, signed_out, and signed_in_text completely unexplained.

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 gives a specific verb and resource: 'Register a site in a profile.' This is clear enough to understand the core action, though 'with the same login identity' is somewhat vague and the description does not differentiate it from siblings such as open or exec.

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 use this tool versus alternatives, no prerequisites, and no exclusions. The phrase 'with the same login identity' hints at context but does not tell an agent when this tool is appropriate.

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 disclose two concrete non-obvious behaviors: it persists the login and the close cascades to all sessions of that profile. It stops short of stating reversibility (can the profile be reopened?), failure behavior for unknown profiles, or permission requirements.

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 short sentence, front-loaded with the action and immediately parenthesizing the cascading effect. Zero waste.

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 one-parameter mutation with no annotations and no output schema, the description covers the main effects but omits reversibility, error cases, and what 'saving the login' actually persists, leaving real gaps an agent must guess at.

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 0% for the single 'profile' parameter, so the description must compensate. It clarifies the parameter's blast radius ('affects all its sessions') but never says whether the value is a name, id, or path, leaving the identifier format undocumented in both places.

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 ('close') and resource ('profile'), plus the non-obvious side effect of saving the login. It's clearly the counterpart to the sibling 'open' tool, though it never names that sibling explicitly.

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: an agent can infer this is the teardown step after working with a profile opened via 'open', but the description never says when to call it versus leaving a profile open or when 'snap'/'remember' should be used instead. No prerequisites or exclusions are given.

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 it does disclose two real traits: code is 'trusted' (security posture) and session variables/helpers persist across calls (state model). It omits what the code executes against, error/failure behavior, the effect of the timeout, and whether the call returns values, which matter greatly for an arbitrary-code-execution 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?

A single front-loaded sentence with no filler. It is efficient but so terse that brevity shades into under-specification rather than disciplined concision.

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 that runs arbitrary code with side effects, accepts four undocumented parameters, has no annotations, and no output schema, one sentence is not enough. An agent cannot tell what the call returns, how failures surface, or how profile and site scope the execution.

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% across four parameters, so the description must compensate and does not. Nothing explains what 'profile' selects, what 'site' binds to, or how 'timeout' is applied; only 'persistent session variables' loosely gestures at why a profile might exist.

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?

Names a specific verb ('Execute') and resource ('Playwright Python'), and adds the distinguishing trait that session variables and helpers persist. It does not explicitly contrast itself with siblings like open, snap, or close, so an agent must infer that exec is the escape hatch for arbitrary scripting rather than the structured navigation tools.

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 description gives no when-to-use guidance and no alternatives: it never says to prefer open/snap for standard navigation and reserve exec for cases those tools cannot express. The word 'trusted' hints at a precondition but is not explained as a usage rule.

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?

No annotations are supplied, so the description carries the full burden. It implies a safe, side-effect-free read by using 'List' and discloses what categories of state come back (profiles, login states, running browsers), but says nothing about cost, permissions, whether it triggers browser launches, or how empty results appear.

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 with zero filler; every clause (profiles, login states, running browsers) adds distinct information about what is returned.

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 parameterless, read-only discovery tool with no output schema, naming the three kinds of state returned is close to sufficient. A note on ordering, emptiness, or how login state is represented would close the 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?

The tool takes zero parameters, so the baseline is 4; the description does not need to explain any inputs and correctly focuses on output content instead.

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 ('local profiles') and enumerates the extra data returned: login states and running browsers. That is more than a restatement of the name, though it does not explicitly contrast itself with any sibling (none of add_site/open/exec/snap/close/remember/memory overlaps, so the cost of that omission is small).

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 statement of when to call this versus alternatives, no prerequisite or ordering hint (e.g. "call before open to pick a profile"), and no exclusions. Usage is only inferable from the tool name and the fact that it lists existing state.

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 at all, the description must carry the full behavioral burden. 'Read' and 'search' imply a safe read, but nothing states whether results are scoped, paginated, ordered, or what an empty/ambiguous site value does, and there is no output schema to fall back on.

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 with no filler. It is efficient, though the terseness comes at the cost of the missing detail rather than being a virtue of restraint.

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?

Three optional parameters, zero schema documentation, no annotations, and no output schema — the description should do substantially more. An agent can guess a path forward but cannot predict which mode it will trigger or what comes back.

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%, so the description must compensate and it does not. It implies 'site' is an identifier and 'search' is a query string, but adds no format, matching semantics, or interaction rules, and the 'profile' parameter is completely unaddressed.

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?

Names two operations (read site notes, search all local notes) against the resource 'memory', which gives an agent a rough idea. However, it never explains what a 'note' or 'site note' actually is, and the third parameter (profile) has no corresponding purpose in the description, so the tool's full scope stays vague.

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?

'or' hints at two modes but gives no conditions for choosing between them (e.g. what happens when both site and search are supplied, or when neither is). No mention of the obvious sibling 'remember' (written by contrast), so an agent gets no routing guidance for the read/write split.

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 definition must carry the full behavioral burden. It does disclose one useful trait (headed opens a local window, implying a visible browser process), but says nothing about side effects, whether a profile is created if absent, what "check login" returns or throws, or whether the operation is synchronous or blocking. For a launch-style tool this is a significant disclosure 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?

A single compact sentence with the core action front-loaded and the window behavior appended as a clarifying clause. Nothing is padded, though the compression contributes to the under-specification noted elsewhere.

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 no annotations, so the description is the only source of behavioral detail, yet it omits return values, error conditions, and three of four parameter meanings. For a tool that launches something and authenticates, an agent is left guessing at critical details.

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% across four parameters, and the definition only explains one of them (headed). The required 'profile' parameter is never clarified (name? id? path?), and 'site' and 'note' receive no mention at all, leaving half the inputs undocumented in both schema and 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 definition names a verb (start) and an object (a profile) plus a secondary check-login action, which gives a rough sense of what happens. However, "profile" is never defined and the framing is abstract, so an agent cannot fully tell whether this launches a browser session, provisions an account, or something else. It is enough to distinguish it from list_profiles or close, but only barely.

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 phrase "on demand" hints at a triggering context but never states when this should be called versus siblings such as list_profiles, exec, or close. No preconditions, no alternatives, no exclusions are given, leaving the agent to infer usage from the tool name alone.

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. 'Append' hints at a write, but it never says whether entries are deduplicated, whether 'local' means per-machine or per-profile, whether writes are reversible, or what permaleness/visibility the stored note has.

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 short sentence with no wasted words and the key verb front-loaded, but the brevity comes from under-specification rather than economy. Nothing is structurally wrong; there is simply too little there.

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 3-required-parameter write tool with no annotations and no output schema, the description supplies nothing about inputs, persistence semantics, or return behavior. An agent cannot call this correctly without trial and error.

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% and there are three required parameters (profile, site, text) that the description never explains. At best 'site' is echoed by the word 'site'; the meaning and expected format of 'profile' and 'text' are left entirely undocumented, which is below the compensation bar for a low-coverage 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?

The fragment 'Append local site know-how' gives a verb (append) and a vague resource ('site know-how'), but never says what a memory entry actually is or what gets persisted. Against a sibling literally named 'memory', an agent cannot tell these two persistence tools apart from the description.

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 statement of when to use this instead of 'memory', 'snap', or other siblings, and no prerequisites or exclusions. The agent must guess the trigger condition entirely.

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?

No annotations are provided, so the description carries the full behavioral burden. Saying 'Read' implies a non-mutating operation, but it does not describe return shape, permissions, whether refs are stable, or how selector/interactive affect behavior. This is a thin behavioral profile for a tool with four undocumented parameters.

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 description is a single front-loaded sentence with no wasted words. It is appropriately terse, though that terseness contributes to gaps elsewhere rather than being a flaw of structure itself.

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 four-parameter tool with no annotations, no output schema, and 0% schema coverage, one sentence is insufficient. An agent cannot infer what selector or interactive do, how site and profile interact, or what the snapshot actually contains.

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% and the description does not name or explain any of the four parameters (site, profile, selector, interactive). 'Session tab' vaguely hints at profile/site context but adds no real semantic value, leaving every parameter undocumented.

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 verb ('Read') and resource ('ARIA snapshot with refs') plus scope ('from the session tab'). It is clear enough to distinguish from siblings like open, exec, and close, though it does not explicitly name alternatives or contrast 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 use this tool versus siblings such as exec or open, nor any prerequisites or exclusions. Usage is only implied by 'session tab' and 'snapshot'.

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